© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22907
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and 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
     ÑĢаÑģп
    -0.08
     Eaton
    -0.08
    å±±æ¹ĸ
    -0.08
    פ×ķ
    -0.08
    ãĤ±ãĥĥãĥĪ
    -0.08
    åĬłçļĦ
    -0.08
    פ×ķת
    -0.07
    åįĩæģ¯
    -0.07
    æĹłä¸Ĭ
    -0.07
    ä¸Ĭæ·»
    -0.07
    POSITIVE LOGITS
    ney
    0.07
     Halle
    0.07
    aleza
    0.07
    åķ¦åķ¦
    0.06
    éĸĴ
    0.06
    æľĿ
    0.06
    yka
    0.06
    Optimizer
    0.06
    yg
    0.06
    uris
    0.06
    Activations Density 0.002%

    No Known Activations