© 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. 28090
    Prev
    Next
    INDEX
    Explanations

    joining us

    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
    以ä¸ĭç®Ģ称
    -0.06
     these
    -0.06
    æŀī
    -0.06
    åħļåĴĮ人æ°ij
    -0.06
    以ä¸ĬåĨħ容
    -0.06
    nos
    -0.05
    ä¹Łå°±æĺ¯
    -0.05
     just
    -0.05
    /msg
    -0.05
    enste
    -0.05
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.12
    åIJĮæł·æĺ¯
    0.08
    ãĤĦãģ¯ãĤĬ
    0.08
    udu
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.08
    engel
    0.08
    å°ıéĿĴ
    0.08
    again
    0.08
    _Framework
    0.08
    ä¸ŃéĿĴ
    0.08
    Activations Density 0.003%

    No Known Activations