© 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. 34660
    Prev
    Next
    INDEX
    Explanations

    names, locations, technical terms

    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
    acci
    -0.07
    å¦Ĥçİī
    -0.07
    çĴIJ
    -0.07
    emet
    -0.07
    ellig
    -0.07
    å¦ĤèĬ±
    -0.07
    åĪ°æľĢåIJİ
    -0.07
    efined
    -0.07
    çŁ¥éģĵçļĦ
    -0.06
    å°±åľ¨è¿ĻæŶ
    -0.06
    POSITIVE LOGITS
    失
    0.07
    èĭ«
    0.07
    åķ¡
    0.07
    ®
    0.06
    ÑĨин
    0.06
    mund
    0.06
    vih
    0.06
    缴æİ¥æĪĸéĹ´æİ¥
    0.06
    ãģĵ
    0.06
    æĵĩ
    0.06
    Activations Density 1.002%

    No Known Activations