© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78552
    Prev
    Next
    INDEX
    Explanations

    conversations and lists

    np_max-act · gemini-2.0-flash

    instructions that request comprehensive, itemized explanations—such as pros and cons, examples for each, or detailed aspects to include—linking multiple elements in a list or comparison.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meyer
    -0.08
    educated
    -0.07
    ﲻ
    -0.07
     Purs
    -0.07
    ues
    -0.07
    ساط
    -0.07
    باط
    -0.07
    изатор
    -0.07
    ied
    -0.06
    ucción
    -0.06
    POSITIVE LOGITS
    (arc
    0.08
    וו
    0.07
    ,const
    0.07
    	UINT
    0.07
    $i
    0.07
    _writer
    0.07
    _CHILD
    0.07
    第三
    0.07
    (vm
    0.07
    的成本
    0.07
    Activations Density 0.143%

    No Known Activations