© 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. 108933
    Prev
    Next
    INDEX
    Explanations

    Blog posts

    np_max-act · gemini-2.0-flash

    Personal, first-person references — especially the pronoun "I" and nearby recent-time adverbs anchoring autobiographical statements.

    oai_token-act-pair · gpt-5-miniTriggered 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
    멋
    -0.08
    איכות
    -0.08
    سياسات
    -0.07
    $objPHPExcel
    -0.07
    ߏ
    -0.07
    nl
    -0.07
    ographical
    -0.07
     diagrams
    -0.07
    裙子
    -0.07
    essment
    -0.07
    POSITIVE LOGITS
    不断增强
    0.08
     UNESCO
    0.07
    .Products
    0.07
    _plus
    0.07
    	virtual
    0.07
    是因为
    0.07
    营利
    0.07
    _distance
    0.07
     Jazeera
    0.07
    Rom
    0.07
    Activations Density 0.196%

    No Known Activations