© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30361
    Prev
    Next
    INDEX
    Explanations

    programming keys

    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
    畅通
    -0.07
     개인
    -0.07
    济南市
    -0.07
     aquatic
    -0.06
    овая
    -0.06
     alterations
    -0.06
     comprend
    -0.06
    市政
    -0.06
     official
    -0.06
     Vac
    -0.06
    POSITIVE LOGITS
    frey
    0.07
    .requireNonNull
    0.07
    oubted
    0.07
    ffield
    0.07
    ﮬ
    0.07
    aha
    0.07
    销量
    0.06
    dba
    0.06
    <len
    0.06
     Jama
    0.06
    Activations Density 0.064%

    No Known Activations