© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45441
    Prev
    Next
    INDEX
    Explanations

    Tamsin Shaw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¢ł
    -0.07
    é¡
    -0.06
     getDescription
    -0.06
     Somma
    -0.06
    她没æľī
    -0.06
    Inverse
    -0.06
    å¹²åĩĢ
    -0.06
    Ted
    -0.06
    isnan
    -0.06
    姨å¨ĺ
    -0.06
    POSITIVE LOGITS
    æĿ¥åIJ§
    0.08
    eron
    0.07
    TRS
    0.07
    utica
    0.07
     tiss
    0.07
    è¿Ļä¹Ī好
    0.07
    emet
    0.07
    å¿ĥ声
    0.06
    zcze
    0.06
    è¿ĻæĿ¡è·¯
    0.06
    Activations Density 0.167%

    No Known Activations