© 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. 62186
    Prev
    Next
    INDEX
    Explanations

    code symbols and punctuation

    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
     perhaps
    -0.08
     maybe
    -0.08
    perhaps
    -0.08
     quizás
    -0.07
    ä¹Łè®¸
    -0.07
     Perhaps
    -0.07
     somehow
    -0.07
     Probably
    -0.07
     vielleicht
    -0.07
    ipp
    -0.07
    POSITIVE LOGITS
    éĢī项ä¸Ń
    0.07
    éªļ
    0.07
    é¢ĺå¹²
    0.06
    ãĤ¤ãĥ¬
    0.06
     اÙĦÙħØ«
    0.06
    èĻ½çĦ¶åľ¨
    0.06
    çĥŃçĥĪçļĦæİĮ声
    0.06
    Ñģлови
    0.06
    èݱçī¹
    0.06
    æľ¬é¢ĺèĢĥæŁ¥
    0.06
    Activations Density 0.002%

    No Known Activations