© 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. 60746
    Prev
    Next
    INDEX
    Explanations

    math and finance logarithms

    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
    å¸ĥè¢ĭ
    -0.07
    INLINE
    -0.07
    à¹Ģà¸ģลà¹īา
    -0.07
    æıIJéĢŁ
    -0.07
    åİħéķ¿
    -0.07
    çļĦåIJĪæĪIJ
    -0.07
    æĿĢæ°Ķ
    -0.07
    .overlay
    -0.07
    Cum
    -0.07
     Cum
    -0.07
    POSITIVE LOGITS
    prem
    0.08
    éĽĦ
    0.07
    éļ
    0.07
    -log
    0.07
    .LOG
    0.07
    log
    0.07
     pisc
    0.07
     pun
    0.07
    .log
    0.07
    æ¹Ľ
    0.07
    Activations Density 0.005%

    No Known Activations