© 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. 72272
    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
     nos
    -0.08
    觊
    -0.08
    𝕝
    -0.07
    _SKIP
    -0.07
    provide
    -0.07
    夙
    -0.06
     لا
    -0.06
    饱满
    -0.06
     reint
    -0.06
     fantasies
    -0.06
    POSITIVE LOGITS
    Cerrar
    0.08
    primaryKey
    0.07
    Disconnect
    0.07
    Permanent
    0.07
    subsection
    0.07
    Decorator
    0.07
    _suffix
    0.06
    .realm
    0.06
     intensely
    0.06
    -par
    0.06
    Activations Density 0.001%

    No Known Activations