© 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. 38920
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
    hone
    -0.07
    .....
    -0.07
    ↵
    -0.07
    åı¯ä»¥åģļ
    -0.07
    âĢ¦..
    -0.07
    è¿ģ
    -0.07
     fiance
    -0.07
    âĢ¦.
    -0.06
    vania
    -0.06
     soucis
    -0.06
    POSITIVE LOGITS
    âĢij
    0.09
    èĴĻå¾·
    0.09
     !)
    0.08
    ±
    0.08
    åĪĺçķħ
    0.08
    ×ŀת
    0.08
    Ö¼
    0.07
    æī§è¡Įå®ĺ
    0.07
    æĪ®
    0.07
     yên
    0.07
    Activations Density 0.003%

    No Known Activations