© 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. 113658
    Prev
    Next
    INDEX
    Explanations

    battlefield

    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
     Ire
    -0.07
    的一些
    -0.07
    .option
    -0.07
     القيام
    -0.07
     acceptance
    -0.06
     Cabin
    -0.06
    围
    -0.06
     związku
    -0.06
    .games
    -0.06
    .i
    -0.06
    POSITIVE LOGITS
     tableName
    0.08
    maal
    0.07
     Schn
    0.07
    懑
    0.07
    dba
    0.07
    .matrix
    0.07
    豹
    0.07
    kids
    0.07
    сор
    0.07
    درس
    0.06
    Activations Density 0.002%

    No Known Activations