© 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. 12826
    Prev
    Next
    INDEX
    Explanations

    medical or technical compounds

    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
     Palmas
    -0.08
     Sims
    -0.08
    HORT
    -0.08
    asted
    -0.08
     feri
    -0.07
    çİīæłij
    -0.07
     Lesser
    -0.07
     inzet
    -0.07
    æ£ļæĪ·
    -0.07
    ç«Ļåľ°éĵģç«Ļ
    -0.07
    POSITIVE LOGITS
    iti
    0.07
    tributes
    0.07
    å¥ī
    0.06
    **
    0.06
    éĤ£è¾¹çļĦ
    0.06
    ubl
    0.06
    èł
    0.06
    خب
    0.06
    æļ´
    0.06
    ç¼ĸåĪ¶
    0.06
    Activations Density 0.319%

    No Known Activations