© 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. 57197
    Prev
    Next
    INDEX
    Explanations

    parallel

    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
    runs
    -0.08
    �
    -0.07
    roat
    -0.07
    ᴶ
    -0.07
    errs
    -0.07
    عق
    -0.07
    &);↵
    -0.07
     //
    -0.07
    時は
    -0.07
    .CG
    -0.07
    POSITIVE LOGITS
     рядом
    0.07
    .Abs
    0.07
    相机
    0.07
     smarty
    0.07
    ponent
    0.07
    .navigate
    0.07
     لدى
    0.07
     لقد
    0.07
     diabetes
    0.06
    必定
    0.06
    Activations Density 0.006%

    No Known Activations