© 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. 60733
    Prev
    Next
    INDEX
    Explanations

    superficialis tendon

    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
    iesz
    -0.08
    asher
    -0.07
    ä¸įåłª
    -0.07
    ä¸į欲
    -0.07
    èĢĮæĹłæ³ķ
    -0.07
    æł¹æľ¬ä¸į
    -0.07
    ahnya
    -0.07
    -exclusive
    -0.07
    asons
    -0.07
    /board
    -0.06
    POSITIVE LOGITS
     especially
    0.08
    åIJĮ声
    0.08
    amel
    0.07
    ziger
    0.07
    åĩłå®¶
    0.07
    åĽłä¸ºæĺ¯
    0.07
    ateg
    0.07
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
    especially
    0.07
    个人认为
    0.07
    Activations Density 0.061%

    No Known Activations