© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic operations

    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
    amah
    -0.07
    é£İåĬĽ
    -0.07
    uli
    -0.06
    ارس
    -0.06
    phis
    -0.06
    ç²Ĺç»Ĩ
    -0.06
    ciu
    -0.06
    emi
    -0.06
    å±±åı£
    -0.06
    æīĭæľºéĺħ读
    -0.06
    POSITIVE LOGITS
    æĴŀ
    0.08
     Conway
    0.08
    ãĤ¢ãĥķ
    0.08
     Increment
    0.07
    ä¿ĥ
    0.07
    åĨįæİ¥åĨį
    0.07
    _increment
    0.07
    秣
    0.07
    èĦĤèĤªéħ¸
    0.07
    increment
    0.07
    Activations Density 0.015%

    No Known Activations