© 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. 22326
    Prev
    Next
    INDEX
    Explanations

    consecutive integers and exponents

    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
    éĮ²
    -0.08
    è¶Ĭ
    -0.07
    æĢ¡
    -0.07
    伤èĢħ
    -0.07
    rene
    -0.07
    chetti
    -0.07
    untime
    -0.07
     голоÑģованиÑı
    -0.07
    LOS
    -0.07
    acer
    -0.07
    POSITIVE LOGITS
    igg
    0.08
    æĪĸå¤ļ
    0.07
    裸
    0.07
    æĥij
    0.07
    å¹³æĸ¹
    0.07
    æ¾İ
    0.07
    /output
    0.07
    Ñĥдо
    0.07
    wand
    0.07
    æľīéĴ±
    0.06
    Activations Density 0.010%

    No Known Activations