© 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. 26429
    Prev
    Next
    INDEX
    Explanations

    statement or end of line

    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
    ä¸ĭåIJĮ
    -0.10
    åı¦è¡ĮéĢļçŁ¥
    -0.07
    оÑģÑĤи
    -0.07
    ?(:
    -0.07
    Ïħνα
    -0.07
    æĻļå®ī
    -0.07
    ntp
    -0.07
    ebt
    -0.07
    udara
    -0.07
    çī¹åĪ«æĺ¯å¯¹
    -0.07
    POSITIVE LOGITS
    è¿Ļæł·ä¸ĢæĿ¥
    0.08
    å¦ĤæŀľæĪij们
    0.07
    åĽłæѤ
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
    è¿ĻæĦıåij³çĿĢ
    0.07
    æį¢åı¥è¯Ŀ说
    0.07
     while
    0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    0.06
    èĢĮè¿ĩ
    0.06
    ائÙĬØ©
    0.06
    Activations Density 0.003%

    No Known Activations