© 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. 64154
    Prev
    Next
    INDEX
    Explanations

    input type definition

    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
    ÃŃda
    -0.07
    িনà§įন
    -0.07
    +xml
    -0.07
    许许å¤ļå¤ļ
    -0.07
    kaar
    -0.07
    ocache
    -0.07
    ä¸ļåĬ¡æµģç¨ĭ
    -0.07
    ÃģT
    -0.07
    гон
    -0.07
     "-
    -0.06
    POSITIVE LOGITS
    Ø´ÙĨ
    0.07
    ëªħíķľ
    0.07
    veld
    0.07
     malad
    0.07
    ×Ļש
    0.06
    _RESERVED
    0.06
    缤纷
    0.06
    ä¹Łå¾Ī大
    0.06
    execute
    0.06
    ponder
    0.06
    Activations Density 0.024%

    No Known Activations