© 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. 70423
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bund
    -0.07
    (endpoint
    -0.07
     Fors
    -0.07
     Accident
    -0.07
     Terrorism
    -0.07
    ть
    -0.07
    erves
    -0.07
     Playback
    -0.07
     Georg
    -0.07
     individ
    -0.06
    POSITIVE LOGITS
    읐
    0.07
     sail
    0.07
    objet
    0.07
     decisión
    0.07
     -----
    0.07
    蜘蛛
    0.07
    ⻄
    0.06
    $I
    0.06
    Pager
    0.06
    잏
    0.06
    Activations Density 0.035%

    No Known Activations