© 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. 51655
    Prev
    Next
    INDEX
    Explanations

    medical terms and classifications

    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¦į
    -0.07
    Fee
    -0.07
    ãģ©
    -0.07
    ä¸įè¡°
    -0.07
    æĪĸä¸į
    -0.06
     Fee
    -0.06
    .opts
    -0.06
    è¯ħ
    -0.06
    æĭ³å¤´
    -0.06
    åĿ
    -0.06
    POSITIVE LOGITS
    åIJĮçIJĨ
    0.10
    æĸ¹éĿ¢çļĦ
    0.10
    å¾·åŁº
    0.09
    æĸ¹éĿ¢ä¹Ł
    0.08
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    ãģ«éĸ¢ãģĹãģ¦ãģ¯
    0.08
    亦çĦ¶
    0.08
    æĸ¹éĿ¢
    0.08
    åĴĮåŁİå¸Ĥ
    0.08
    Activations Density 0.051%

    No Known Activations