© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23276
    Prev
    Next
    INDEX
    Explanations

    consequences and possibilities

    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
    _deps
    -0.08
    erner
    -0.07
    举åįİ
    -0.07
    çĽĺä¸Ń
    -0.07
    à°¡à°¿
    -0.07
    çĻ¾
    -0.07
    为åijĺå·¥
    -0.07
    issons
    -0.07
    à¹īา
    -0.07
    DIC
    -0.07
    POSITIVE LOGITS
     uniqueness
    0.08
    åĪ«æĹł
    0.07
    /Peak
    0.07
    å¿ĺåį´
    0.07
    ekl
    0.07
     Hidalgo
    0.07
    ä¸įåı¯æĽ¿ä»£
    0.07
     similarities
    0.07
    åĩŃçĿĢ
    0.06
     competitors
    0.06
    Activations Density 0.010%

    No Known Activations