© 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. 83453
    Prev
    Next
    INDEX
    Explanations

    is

    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
    NavItem
    -0.08
     назначен
    -0.07
     engaging
    -0.07
    logging
    -0.07
    因为在
    -0.07
    anges
    -0.07
    ной
    -0.07
    쪗
    -0.07
     alleged
    -0.07
    处在
    -0.07
    POSITIVE LOGITS
    ﻲ
    0.07
    toUpperCase
    0.07
    肇事
    0.07
     العمر
    0.07
    륨
    0.07
    .tabs
    0.07
    .BACK
    0.06
     tất
    0.06
    ורי
    0.06
    طي
    0.06
    Activations Density 0.062%

    No Known Activations