© 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. 113690
    Prev
    Next
    INDEX
    Explanations

    Latex math formulas

    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
     usa
    -0.07
    Getter
    -0.07
    嶓
    -0.07
     divisive
    -0.07
     contributing
    -0.07
     TLC
    -0.07
    _geometry
    -0.06
     comprises
    -0.06
    遗
    -0.06
    .rating
    -0.06
    POSITIVE LOGITS
    (th
    0.07
     Microsoft
    0.07
    ATORY
    0.07
    _EOL
    0.07
    *w
    0.07
     Sidney
    0.07
    .quality
    0.06
    weapons
    0.06
    .TestTools
    0.06
    book
    0.06
    Activations Density 0.005%

    No Known Activations