© 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. 80303
    Prev
    Next
    INDEX
    Explanations

    Judaism

    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
    兒
    -0.08
     meilleurs
    -0.07
    𝗨
    -0.07
     compass
    -0.06
    になれ
    -0.06
    compass
    -0.06
     nevertheless
    -0.06
    utton
    -0.06
    ทร
    -0.06
    -built
    -0.06
    POSITIVE LOGITS
    /interfaces
    0.07
    Cantidad
    0.07
     attachments
    0.07
    ONGO
    0.07
     sweaty
    0.07
     dataType
    0.07
    غرب
    0.06
    /swagger
    0.06
    ços
    0.06
     sidew
    0.06
    Activations Density 0.003%

    No Known Activations