© 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. 19066
    Prev
    Next
    INDEX
    Explanations

    specifying context or function

    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
    reich
    -0.08
     ëįĶ보기
    -0.08
    rowable
    -0.08
    javax
    -0.07
    çļĦåıijå±ķåĴĮ
    -0.07
    æĬ¥åIJįæŶéĹ´
    -0.07
    reif
    -0.07
    orners
    -0.07
    angguan
    -0.07
    umbang
    -0.07
    POSITIVE LOGITS
     Aga
    0.07
    æĪIJçļĦ
    0.07
    è¦Ĩ
    0.06
    ACC
    0.06
    ELTS
    0.06
    iling
    0.06
    imetr
    0.06
    å¿Ĩ
    0.06
     Barnes
    0.06
    马æĸ¯
    0.06
    Activations Density 0.475%

    No Known Activations