© 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. 120236
    Prev
    Next
    INDEX
    Explanations

    Job descriptions

    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
    慣れ
    -0.07
    于是
    -0.07
     inferior
    -0.07
    ながら
    -0.07
     triumph
    -0.07
     هذه
    -0.06
    INST
    -0.06
    chw
    -0.06
    拿到
    -0.06
     heightened
    -0.06
    POSITIVE LOGITS
    specifier
    0.08
    abama
    0.08
    党工委
    0.07
     gözü
    0.07
    班车
    0.07
    水墨
    0.07
     mRNA
    0.07
     gunmen
    0.07
    rarian
    0.07
    跚
    0.07
    Activations Density 0.127%

    No Known Activations