© 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. 60705
    Prev
    Next
    INDEX
    Explanations

    static descriptions or attributes

    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
    åħħ
    -0.08
     EDUCA
    -0.07
    acci
    -0.07
    iphone
    -0.07
    /DTD
    -0.06
    .bmp
    -0.06
    çŃĶé¢ĺåį¡
    -0.06
    hea
    -0.06
     Manning
    -0.06
    -0.06
    POSITIVE LOGITS
     https
    0.07
    âĸ¼
    0.07
    绾ç»İ
    0.07
    https
    0.06
    å¿ĺä¸įäºĨ
    0.06
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.06
    ìĤ¬ë¡ľ
    0.06
    (crate
    0.06
    ç¿©ç¿©
    0.06
    èªĩ
    0.06
    Activations Density 0.010%

    No Known Activations