© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 31729
    Prev
    Next
    INDEX
    Explanations

    current situation

    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
    å¤ĸéĢģ
    -0.07
    flash
    -0.06
     contours
    -0.06
    æĺ¯äººä»¬
    -0.06
    ä¸Ģå®ļ
    -0.06
    onial
    -0.06
    æĺŁæľŁå¤©
    -0.06
    én
    -0.06
     certain
    -0.06
     incident
    -0.06
    POSITIVE LOGITS
    ospace
    0.08
    å°ģç¥ŀ
    0.08
    usk
    0.08
    åIJįæĢĿ
    0.07
    å¯ĮåĬĽ
    0.07
    áĥ£áĥ¡
    0.07
    ози
    0.07
    ikit
    0.07
    elda
    0.07
    RITE
    0.07
    Activations Density 0.001%

    No Known Activations