© 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. 57084
    Prev
    Next
    INDEX
    Explanations

    mathematical function 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
    itta
    -0.08
    人åijĺåIJįåįķ
    -0.07
     latter
    -0.07
    è¿ĺç»Ļ
    -0.07
    åIJİèĢħ
    -0.07
    rint
    -0.07
    èħĬèĤī
    -0.07
    ä¼´ä½ł
    -0.07
    hra
    -0.07
     découvrez
    -0.07
    POSITIVE LOGITS
    ##_
    0.07
    æĭ¼
    0.07
    çĪĨè£Ĥ
    0.07
     Kamar
    0.06
     Starter
    0.06
     Pej
    0.06
    èĪĴ
    0.06
     Kop
    0.06
    ownt
    0.06
    æĪijæĿ¥
    0.06
    Activations Density 0.039%

    No Known Activations