© 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. 64912
    Prev
    Next
    INDEX
    Explanations

    code keywords and definitions

    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
    容
    -0.08
    estina
    -0.07
    ä¸įèĭŁ
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    _bounds
    -0.07
    omatik
    -0.07
    ergen
    -0.07
    refs
    -0.06
    _elems
    -0.06
    âĵĴ
    -0.06
    POSITIVE LOGITS
    utton
    0.07
    sche
    0.07
    ¡´
    0.07
    nut
    0.06
    åĮ¿åIJįçĶ¨æĪ·
    0.06
    βο
    0.06
    课ä¸Ĭ
    0.06
    ÙĪرش
    0.06
    ä¸ĭä¸Ģç¯ĩ
    0.06
    strike
    0.06
    Activations Density 0.023%

    No Known Activations