© 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. 11-RESID-POST-AA
    11. 112893
    Prev
    Next
    INDEX
    Explanations

    negativity

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assigned
    -0.07
     short
    -0.07
     cu
    -0.07
     Poz
    -0.06
     bois
    -0.06
     preventive
    -0.06
    $',
    -0.06
    .unique
    -0.06
    ugi
    -0.06
    喘
    -0.06
    POSITIVE LOGITS
    玩法
    0.07
    在網路上
    0.07
    ログ
    0.07
    眼中
    0.07
    -Control
    0.07
    _rows
    0.06
     girlfriend
    0.06
    Constraints
    0.06
    _charset
    0.06
     egregious
    0.06
    Activations Density 0.039%

    No Known Activations