© 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. 64592
    Prev
    Next
    INDEX
    Explanations

    actors guild awards

    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
    strup
    -0.07
     quarter
    -0.07
    ÅĤon
    -0.07
    roid
    -0.06
    otis
    -0.06
    è®°äºĭ
    -0.06
     Niel
    -0.06
    ijski
    -0.06
    ấp
    -0.06
    麦å½ĵ
    -0.06
    POSITIVE LOGITS
    ranti
    0.07
     wiz
    0.07
    å°±åĽłä¸º
    0.07
    åİŁåĽłæĺ¯
    0.07
    æĢ»æ¯Ķ
    0.07
    åİŁåĽłå°±æĺ¯
    0.07
    shiv
    0.07
    epro
    0.06
    ogue
    0.06
    æīĢéķ¿
    0.06
    Activations Density 0.071%

    No Known Activations