© 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. 63699
    Prev
    Next
    INDEX
    Explanations

    medical / surgical procedures

    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
    ä¹ĭ乡
    -0.08
    å²Ń
    -0.07
    abor
    -0.07
    ack
    -0.07
    _EXEC
    -0.06
    hf
    -0.06
    éģŃåıĹ
    -0.06
    миÑĢ
    -0.06
    顺åĪ©å®ĮæĪIJ
    -0.06
    ownt
    -0.06
    POSITIVE LOGITS
    ราย
    0.08
    æ¯Ķè¾ĥé«ĺ
    0.07
    羣æŃ£åľ°
    0.07
    ignes
    0.07
    вÑĥ
    0.07
    /jav
    0.07
    _BOTH
    0.07
    _trade
    0.07
    imers
    0.07
    ارات
    0.07
    Activations Density 0.027%

    No Known Activations