© 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. 15-RESID-POST-AA
    11. 5457
    Prev
    Next
    INDEX
    Explanations

    probability/likelihood

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ٷ
    -0.07
     documentation
    -0.07
    влекатель
    -0.07
    ﻔ
    -0.06
    pace
    -0.06
    -z
    -0.06
    ;padding
    -0.06
     безопасности
    -0.06
    >f
    -0.06
    olson
    -0.06
    POSITIVE LOGITS
     işaret
    0.07
    _formula
    0.07
     Tart
    0.07
     مباشرة
    0.07
     ||
↵
    0.07
     intact
    0.07
     smooth
    0.07
     Geological
    0.07
    .TextAlign
    0.07
     перемен
    0.07
    Activations Density 0.039%

    No Known Activations