© 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. 29685
    Prev
    Next
    INDEX
    Explanations

    Computer, programming

    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
    apyrus
    -0.07
     Fitz
    -0.07
     vile
    -0.07
    .used
    -0.07
    댈
    -0.07
     controversy
    -0.07
    .tv
    -0.07
     amend
    -0.07
     Stefan
    -0.07
    📩
    -0.07
    POSITIVE LOGITS
    Schema
    0.07
    ents
    0.07
     располож
    0.06
    大会上
    0.06
    gle
    0.06
    体现了
    0.06
     Nes
    0.06
    食材
    0.06
    ştırma
    0.06
     peasant
    0.06
    Activations Density 0.193%

    No Known Activations