© 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. 63235
    Prev
    Next
    INDEX
    Explanations

    Devanagari numbers and punctuation

    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
    è¿
    -0.06
    çĭŀ
    -0.06
    agn
    -0.06
    è®¤çľŁåģļ好
    -0.06
    éĺŁ
    -0.06
    ä¸įçĦ¶
    -0.05
    ä¹ĸ
    -0.05
    æīĵåľ¨
    -0.05
    -ins
    -0.05
    же
    -0.05
    POSITIVE LOGITS
    èĭ±æĸĩåIJį称
    0.08
    .Named
    0.08
    denes
    0.08
    ä¸įäºĨçļĦ
    0.08
    SharedPtr
    0.08
    ỡ
    0.08
    quilla
    0.07
    ÄĻż
    0.07
    åIJįåŃĹçļĦ
    0.07
    LANG
    0.07
    Activations Density 0.001%

    No Known Activations