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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76233
    Prev
    Next
    INDEX
    Explanations

    thought

    np_max-act · gemini-2.0-flash
    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
    ился
    -0.07
     counts
    -0.07
    —the
    -0.07
    ﾝ
    -0.07
    —they
    -0.06
     degradation
    -0.06
    —he
    -0.06
    —"
    -0.06
    op
    -0.06
    众多
    -0.06
    POSITIVE LOGITS
     proble
    0.07
    枍
    0.07
     gover
    0.07
     Latter
    0.06
    _equalTo
    0.06
    亲眼
    0.06
    tips
    0.06
     сли
    0.06
     HI
    0.06
     murderers
    0.06
    Activations Density 0.038%

    No Known Activations