© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    percentile ranking

    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
    ighth
    -0.07
    æĭħ
    -0.07
    -temp
    -0.06
    itemap
    -0.06
    å¾®
    -0.06
    åĴĮæľįåĬ¡
    -0.06
    ots
    -0.06
     citizen
    -0.06
    éŁ³
    -0.06
    ä¸İåıijå±ķ
    -0.06
    POSITIVE LOGITS
    æĪĸèĢħ缴æİ¥
    0.10
    æĪĸèĢħ说
    0.09
    æĪĸ缴æİ¥
    0.08
    ghan
    0.07
    chaft
    0.07
     fras
    0.07
    enner
    0.07
    ently
    0.07
    anners
    0.07
    trag
    0.07
    Activations Density 0.043%

    No Known Activations