© 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. 20810
    Prev
    Next
    INDEX
    Explanations

    Yin and Yang

    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
    èĢIJåĬ³
    -0.09
    ings
    -0.09
    ãĤĪãģĨãģ«ãģªãĤĭ
    -0.09
    窿
    -0.08
    帼
    -0.08
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    -0.08
    à¸Ĭาà¸ķิ
    -0.08
    ãĤĪãģĨãģ«ãģªãģ£ãģ¦
    -0.08
    chaft
    -0.07
    ãĤĪãģĨãģ«ãģªãĤĬãģ¾ãģĻ
    -0.07
    POSITIVE LOGITS
    rous
    0.09
    ½
    0.08
    æĸ°å®¿
    0.08
    urga
    0.08
    ensive
    0.08
    sha
    0.08
    cere
    0.08
    zelfde
    0.08
    upo
    0.07
    æĸ¯åħĭ
    0.07
    Activations Density 0.006%

    No Known Activations