© 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. 31140
    Prev
    Next
    INDEX
    Explanations

    copyright or license

    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
    æĸ°åĬłåĿ¡
    -0.09
    ÑĪеÑĢ
    -0.07
    ä¸Ńæļij
    -0.07
    ãĤ¤ãĥ¬
    -0.07
    ivin
    -0.06
    ì°¬
    -0.06
    ãĥ«ãĥĪ
    -0.06
    reven
    -0.06
    .twig
    -0.06
    ืà¸Ļ
    -0.06
    POSITIVE LOGITS
    NotFoundError
    0.08
    æŁIJæŁIJ
    0.07
    çİĭæ°ı
    0.07
    åĪĩéĻ¤æľ¯
    0.07
    TextNode
    0.07
    orida
    0.07
    åĽłç´łå½±åĵį
    0.07
    å·¥ç¨ĭä¸ĵä¸ļ
    0.07
    acco
    0.07
    æķĻèĤ²å·¥ä½ľ
    0.07
    Activations Density 1.278%

    No Known Activations