© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 130250
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    Negative Logits
    Locker
    -0.07
     Lind
    -0.07
    TEST
    -0.07
    Unexpected
    -0.07
     tard
    -0.07
    Present
    -0.07
     moss
    -0.07
    .visitVarInsn
    -0.06
     immigrants
    -0.06
    _BUFFER
    -0.06
    POSITIVE LOGITS
    ﯻ
    0.07
    atically
    0.07
    上映
    0.07
    涨幅
    0.07
    Tahoma
    0.07
    .Show
    0.07
    aturas
    0.06
    .Pages
    0.06
     liberties
    0.06
    上海市
    0.06
    Activations Density 0.010%

    No Known Activations