© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21637
    Prev
    Next
    INDEX
    Explanations

    cell growth, disease, protein

    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
    å¿ł
    -0.06
     hoogte
    -0.06
    ython
    -0.06
    æѤ
    -0.06
    ala
    -0.06
    dest
    -0.06
    éľ
    -0.06
    Kit
    -0.06
    天å¤ĸ
    -0.06
    ry
    -0.06
    POSITIVE LOGITS
    ç³»åĪĹ
    0.09
    ç§įç±»
    0.09
     ìĭľë¦¬ì¦Ī
    0.09
    ç±»åĴĮ
    0.09
    ä¹ĭä¸ĢçļĦ
    0.09
    ãĤ·ãĥªãĥ¼ãĤº
    0.09
    WithType
    0.08
    éĽ¨éĽª
    0.08
    argon
    0.08
    ç³»åĪĹçļĦ
    0.08
    Activations Density 0.302%

    No Known Activations