© 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. 27647
    Prev
    Next
    INDEX
    Explanations

    importance, accuracy, role, effects

    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
    leur
    -0.08
    less
    -0.08
    icious
    -0.07
    asional
    -0.07
    oji
    -0.07
    ash
    -0.07
    åĿ¦
    -0.07
    walker
    -0.06
    è´¨
    -0.06
    lecht
    -0.06
    POSITIVE LOGITS
    ä¸İç»ıæµİ
    0.09
    åĴĮæ³ķå¾ĭ
    0.08
    åĴĮæĶ¿æ²»
    0.08
    åĴĮ社ä¼ļ
    0.08
    åĴĮç»ıæµİ
    0.08
    ä¸İ伦
    0.07
    exterity
    0.07
    jän
    0.07
    åĴĮèīºæľ¯
    0.07
    /legal
    0.07
    Activations Density 0.764%

    No Known Activations