© 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. 44084
    Prev
    Next
    INDEX
    Explanations

    medical and science jargon

    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
    é¦ĸéĥ¨
    -0.09
    å©
    -0.08
    /ay
    -0.08
    ç¥ŀ殿
    -0.08
    天åłĤ
    -0.08
    楼顶
    -0.08
    èĪįå¾Ĺ
    -0.07
    øy
    -0.07
     ÑģÑĤеÑĢ
    -0.07
    okuva
    -0.07
    POSITIVE LOGITS
    åľĪ
    0.07
    COVER
    0.07
     rested
    0.06
    _provider
    0.06
    RS
    0.06
     Bur
    0.06
    CS
    0.06
     resting
    0.06
    reis
    0.06
    æľ¯
    0.06
    Activations Density 0.007%

    No Known Activations