© 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. 46990
    Prev
    Next
    INDEX
    Explanations

    trisubstituted

    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
     Trot
    -0.07
    éľĨ
    -0.07
    éĽ
    -0.07
     apart
    -0.07
    çŧ
    -0.07
    haus
    -0.07
    que
    -0.07
    lot
    -0.06
    å¦ĤåĪĿ
    -0.06
     either
    -0.06
    POSITIVE LOGITS
    udas
    0.08
     Voll
    0.07
    èĴĻå¾·
    0.07
    ç¨ĭ度çļĦ
    0.07
    æĬļ
    0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    0.07
    ç¨ĭ度
    0.07
    ologne
    0.07
     getType
    0.07
    licit
    0.07
    Activations Density 0.002%

    No Known Activations