© 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. 113771
    Prev
    Next
    INDEX
    Explanations

    releases and openings

    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
    甲状
    -0.07
     enthusiasm
    -0.07
    腧
    -0.07
     Shiite
    -0.06
     ihtiya
    -0.06
    GY
    -0.06
    ographed
    -0.06
    -g
    -0.06
    Ĥ
    -0.06
    מוס
    -0.06
    POSITIVE LOGITS
     render
    0.08
    的行为
    0.07
    并不
    0.07
    诗词
    0.07
    Tab
    0.07
    _sm
    0.07
    .permission
    0.07
    _AN
    0.07
     применения
    0.07
    하며
    0.07
    Activations Density 0.092%

    No Known Activations