© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20793
    Prev
    Next
    INDEX
    Explanations

    proofs and equations

    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
    idge
    -0.07
    spi
    -0.07
    els
    -0.07
    ãĥĥãĤº
    -0.07
    è¢ŃæĿ¥
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.06
    [](
    -0.06
    weichen
    -0.06
    åĪļåĪļå¼Ģå§ĭ
    -0.06
     ((_
    -0.06
    POSITIVE LOGITS
    åĨįè¿ĩ
    0.08
    ousy
    0.07
    Äħż
    0.07
    æīĢä½ľ
    0.07
    /generated
    0.07
    oug
    0.06
    oir
    0.06
    趾
    0.06
    OMA
    0.06
    icca
    0.06
    Activations Density 0.003%

    No Known Activations