© 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. 28254
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with punctuation

    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
    ron
    -0.07
    ow
    -0.07
    pal
    -0.06
    ten
    -0.06
    ç¼¥
    -0.06
    ç²¾ç¥ŀåĴĮ
    -0.06
    umm
    -0.06
    pri
    -0.06
    å¯Ħ
    -0.06
    pah
    -0.06
    POSITIVE LOGITS
    ystate
    0.08
    ezza
    0.07
    iono
    0.07
    वान
    0.07
    ä¸ĭ称
    0.07
    åľ³
    0.07
    ä¸ĭåIJĮ
    0.07
    reds
    0.07
    )=
    0.07
    uez
    0.07
    Activations Density 0.013%

    No Known Activations