© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    degree, formula, service, therapy

    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
    就差
    -0.08
    wah
    -0.07
    iphy
    -0.07
    į¼
    -0.07
    ânia
    -0.07
    λια
    -0.07
    ä¸ŃçļĦéĩįè¦ģ
    -0.07
    大æīĵæĬĺæī£
    -0.07
    .putExtra
    -0.07
    è®©æĽ´å¤ļ
    -0.07
    POSITIVE LOGITS
     bersifat
    0.11
    æĺ¯ä¸įåı¯
    0.09
    åĽłä¸ºæĺ¯
    0.09
    æĹłå®³
    0.09
    èĢĮä¸Ķæĺ¯
    0.09
    åijĪ
    0.09
    å®īåħ¨åı¯éĿł
    0.08
     ÑģÑĤÑĢого
    0.08
    å¿ħé¡»æĺ¯
    0.08
    ä¿ĿæĮģ稳å®ļ
    0.08
    Activations Density 0.450%

    No Known Activations