© 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. 7-RESID-POST-AA
    11. 79269
    Prev
    Next
    INDEX
    Explanations

    cookies

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    菌
    -0.07
    ین
    -0.07
    İZ
    -0.06
     Zombies
    -0.06
    ับ
    -0.06
     spac
    -0.06
    IDO
    -0.06
    阐释
    -0.06
    .PreparedStatement
    -0.06
    صن
    -0.06
    POSITIVE LOGITS
     siege
    0.08
    洛阳
    0.07
     langu
    0.06
     Lines
    0.06
    _phase
    0.06
    _GT
    0.06
     clauses
    0.06
     تت
    0.06
     Gerr
    0.06
     virtually
    0.06
    Activations Density 0.587%

    No Known Activations