© 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. 39945
    Prev
    Next
    INDEX
    Explanations

    Âł character

    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
    à¥įड
    -0.09
    dbuf
    -0.09
    æľ¬æĸĩéĵ¾æİ¥
    -0.09
    ÙĬÙĬÙĨ
    -0.08
    isial
    -0.08
    äºĭåħĪ
    -0.08
     jull
    -0.08
    ingar
    -0.08
    à¸Ļà¸Ńà¸ĩ
    -0.08
    æĹłå¥ĪçļĦ
    -0.08
    POSITIVE LOGITS
    Âł
    0.09
    ï¸İ
    0.08
    urch
    0.07
    ness
    0.07
     Âł
    0.06
    翼翼
    0.06
    å¥ĩ
    0.06
    incon
    0.06
    glm
    0.06
    ¬
    0.06
    Activations Density 0.146%

    No Known Activations