© 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. 43654
    Prev
    Next
    INDEX
    Explanations

    mathematicalexpressions with parentheses

    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
    оÑĩе
    -0.07
    udded
    -0.07
    eram
    -0.07
    éļĶç»Ŀ
    -0.07
    fass
    -0.07
    cpt
    -0.06
    urio
    -0.06
    hoff
    -0.06
    _once
    -0.06
    iola
    -0.06
    POSITIVE LOGITS
    ENAME
    0.07
    éĥ½åIJĪ
    0.07
    åij½
    0.07
    ETHER
    0.07
    rending
    0.07
     taxation
    0.07
    yntax
    0.06
    ÙĦÛĮ
    0.06
    è¿IJä½ľ
    0.06
    ERVED
    0.06
    Activations Density 0.006%

    No Known Activations