© 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. 17803
    Prev
    Next
    INDEX
    Explanations

    a

    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
     tow
    -0.07
    -ring
    -0.07
    Ze
    -0.07
    Egypt
    -0.06
     teil
    -0.06
     Relationships
    -0.06
    ⽴
    -0.06
    (sound
    -0.06
    -pop
    -0.06
    (isset
    -0.06
    POSITIVE LOGITS
    herits
    0.08
    ⬊
    0.07
    💅
    0.07
    겉
    0.07
    崂
    0.07
     miłości
    0.07
    عبة
    0.07
     عربي
    0.06
    VML
    0.06
    支援
    0.06
    Activations Density 0.019%

    No Known Activations