© 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. 56541
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    ä¸įéĶĻäºĨ
    -0.07
    Õ
    -0.07
    althy
    -0.07
    orch
    -0.07
    ilinear
    -0.07
    artige
    -0.07
    øm
    -0.06
    úra
    -0.06
    ered
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
    portun
    0.10
    æ°´ä»Ļ
    0.09
     COPYRIGHT
    0.08
    intér
    0.08
    burgh
    0.08
    stellen
    0.08
    xffffff
    0.08
    ìĭľíĶ¼
    0.08
    xffff
    0.07
    COPY
    0.07
    Activations Density 0.309%

    No Known Activations