© 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. 24002
    Prev
    Next
    INDEX
    Explanations

    e.g., technical or code terms

    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
    åīį款
    -0.07
    ospace
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
    ÐķÐļ
    -0.06
    ÙĬÙĦØ©
    -0.06
    è¿ĩ头
    -0.06
    Parsing
    -0.06
     Vent
    -0.06
    æĹ©çŁ¥éģĵ
    -0.06
    urras
    -0.06
    POSITIVE LOGITS
    лÑĸй
    0.08
    /goto
    0.07
    /pm
    0.07
    /bower
    0.07
    ObjectContext
    0.07
    @index
    0.07
    arf
    0.07
    ä¸ľå±±
    0.07
     PROGMEM
    0.07
    é¢Ĩ导åıĬ
    0.07
    Activations Density 0.141%

    No Known Activations