© 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. 19252
    Prev
    Next
    INDEX
    Explanations

    mathematical ratios and fractions

    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
    tiv
    -0.08
    èĨ½
    -0.08
    èĥĨ
    -0.07
    åĨ²è¿Ľ
    -0.07
     наÑĩи
    -0.07
    æıĴä¸Ĭ
    -0.07
    å¼¥
    -0.07
    åĪ
    -0.07
    æļ§
    -0.06
    лк
    -0.06
    POSITIVE LOGITS
     asympt
    0.08
    ultimate
    0.07
    åŃ¢
    0.07
    大è§Ĥ
    0.07
     Criterion
    0.07
    riterion
    0.07
    à¸ķัà¸Ķ
    0.07
    rada
    0.07
    ergi
    0.07
    burger
    0.07
    Activations Density 0.003%

    No Known Activations