© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39438
    Prev
    Next
    INDEX
    Explanations

    names after fraction or following academic titles

    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
    çĢļ
    -0.08
    èĻ«çĹħ
    -0.08
    óc
    -0.06
    太åĴĮ
    -0.06
    oom
    -0.06
    å²Ń
    -0.06
    西æĸ¯
    -0.06
    jang
    -0.06
    漫漫
    -0.06
     Jag
    -0.06
    POSITIVE LOGITS
    åĪĢçīĩ
    0.08
     облаÑģÑĤной
    0.07
    ç¼ĸæİĴ
    0.07
    edly
    0.07
    éĩİçĶŁ
    0.07
    é¡¹çĽ®åľ¨
    0.07
    ÄĽj
    0.07
     autoria
    0.07
    usters
    0.07
    asca
    0.07
    Activations Density 0.094%

    No Known Activations