© 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. 33861
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with symbols

    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
    Ø©
    -0.10
    ation
    -0.09
    age
    -0.08
    ados
    -0.07
    ¶
    -0.07
    amento
    -0.07
    éħ¸éĴ¾
    -0.07
    à¸ķร
    -0.07
    uzu
    -0.07
    otle
    -0.07
    POSITIVE LOGITS
    nya
    0.11
    ÛĮ
    0.11
    俱ä¹IJéĥ¨
    0.10
    ious
    0.10
    çļĦ
    0.09
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.09
    ä¸įåı¯æĢĿè®®
    0.09
    ient
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    ãģ®ãģ§
    0.07
    Activations Density 0.003%

    No Known Activations