© 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. 57594
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
    ipan
    -0.08
    å²Ľ
    -0.07
    ä¸įä½ıçļĦ
    -0.07
    å²ĽçļĦ
    -0.07
    ä¸įçł´
    -0.07
    geh
    -0.07
    mira
    -0.06
    æ²³æºIJ
    -0.06
    éĤij
    -0.06
    rack
    -0.06
    POSITIVE LOGITS
    ught
    0.08
    èĢĮèµ°
    0.07
    olley
    0.07
    alyzed
    0.07
    æĸĽ
    0.07
    unique
    0.07
    ä¸ĩ亿
    0.06
    解åĨ³éĹ®é¢ĺçļĦèĥ½åĬĽ
    0.06
    UGHT
    0.06
    endez
    0.06
    Activations Density 0.021%

    No Known Activations