© 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. 19802
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
    affer
    -0.08
    visor
    -0.07
    aus
    -0.07
    aims
    -0.07
    obot
    -0.07
    éĻ¨
    -0.07
    inqu
    -0.06
     ÑĪÑĥма
    -0.06
    uzzer
    -0.06
    åľ¨åIJĦ个
    -0.06
    POSITIVE LOGITS
    arik
    0.07
     ${(
    0.07
    å¹³è¡Į
    0.07
    æ¥Ń
    0.07
    parallel
    0.06
    æīĭæĭ¿
    0.06
    è¿ĺæĺ¯æ²¡æľī
    0.06
    ower
    0.06
    ibel
    0.06
     Parallel
    0.06
    Activations Density 0.103%

    No Known Activations