© 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. 25564
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

    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
    á»įt
    -0.08
     irres
    -0.07
    ä¹ĭå·®
    -0.07
    çľĭä¸įåĩº
    -0.07
    çŃĸ
    -0.07
     Alone
    -0.07
    éĵģé¾Ļ
    -0.07
    mato
    -0.06
    åĴ¨
    -0.06
    æĩĪ
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶ä¸įæĺ¯
    0.10
    (optional
    0.09
    optional
    0.09
     incidental
    0.09
     optional
    0.09
     briefly
    0.08
     pertin
    0.08
    åı¯ä»¥ä½ľä¸º
    0.08
     broader
    0.08
    åıªæĺ¯ä¸ºäºĨ
    0.08
    Activations Density 0.016%

    No Known Activations