© 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. 8181
    Prev
    Next
    INDEX
    Explanations

    code and programming examples

    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
    ç§
    -0.07
    uner
    -0.06
    ajs
    -0.06
    plom
    -0.06
    ç¨ĭ
    -0.06
     THPT
    -0.06
    anged
    -0.06
    è¶Ĭ
    -0.06
    寿
    -0.06
    каде
    -0.06
    POSITIVE LOGITS
    umon
    0.08
    è¿Ļå°±æĺ¯æĪij
    0.08
    äºīåĪĽ
    0.07
    èİ·åıĸæĽ´å¤ļ
    0.07
    _multiplier
    0.07
    tuv
    0.07
    æĮĩçĤ¹
    0.07
    yn
    0.07
    .parseFloat
    0.07
    ãĥįãĤ¹
    0.07
    Activations Density 0.003%

    No Known Activations