© 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. 61250
    Prev
    Next
    INDEX
    Explanations

    case numbers and periods

    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
    èĵ¬
    -0.08
    è¿ŀ
    -0.07
    å¼Ģåħ·
    -0.07
    upal
    -0.07
    acca
    -0.07
    aly
    -0.06
    æĹ¢ä¸į
    -0.06
    à¯ģà®ķ
    -0.06
    派对
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
    _mime
    0.07
    俱ä¹IJéĥ¨
    0.07
    ctrine
    0.07
    Ïĩεί
    0.07
    coli
    0.07
    .tem
    0.07
    å¤ĦçIJĨ好
    0.07
    nikom
    0.07
    妩
    0.07
    Ñģполни
    0.07
    Activations Density 0.007%

    No Known Activations