© 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. 31273
    Prev
    Next
    INDEX
    Explanations

    character codes and letters

    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
    æ³¥æµĨ
    -0.08
    è¯ŃéŁ³æŶéķ¿
    -0.07
    ibat
    -0.07
    ezo
    -0.07
    ört
    -0.07
    _EPS
    -0.07
    åı£å¾Ħ
    -0.07
    /moment
    -0.07
    é¤ħ
    -0.07
     TIMEOUT
    -0.07
    POSITIVE LOGITS
    .charCodeAt
    0.10
     alph
    0.10
    abcdefghijklmnopqrstuvwxyz
    0.08
     LETTER
    0.08
     alphabet
    0.08
    .ascii
    0.08
    åŃĹæ¯į
    0.07
    à¸ļุ
    0.07
     letter
    0.07
     alphabetical
    0.07
    Activations Density 0.023%

    No Known Activations