© 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. 43083
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
     presta
    -0.08
    âĸ·
    -0.08
    rott
    -0.08
    resse
    -0.08
    èIJ¥ä¸ļé¢Ŀ
    -0.07
    URI
    -0.07
    ÙĪغ
    -0.07
    amed
    -0.07
    wik
    -0.07
    odata
    -0.07
    POSITIVE LOGITS
    wort
    0.07
     önc
    0.06
    ACES
    0.06
    ä¸ĢæĹı
    0.06
    )||(
    0.06
    éĩijåŃĹ
    0.06
    acea
    0.06
    Sync
    0.06
    frig
    0.06
    abt
    0.06
    Activations Density 0.166%

    No Known Activations