© 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. 4508
    Prev
    Next
    INDEX
    Explanations

    probability of sequences with fractions

    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
    åįĬæŃ¥
    -0.08
    åľ¨ä»»ä½ķ
    -0.08
     Reform
    -0.08
    ç¥ĸå®Ĺ
    -0.08
    Cole
    -0.08
     reform
    -0.08
    ä¸ĢåĬ¨
    -0.07
    -host
    -0.07
    ASAN
    -0.07
     everytime
    -0.07
    POSITIVE LOGITS
     quint
    0.08
     exponentially
    0.08
     exponential
    0.07
    åĽĽçº§
    0.06
     (((
    0.06
    .cum
    0.06
     Lod
    0.06
    .ld
    0.06
    ç«ĭæĸ¹
    0.06
     final
    0.06
    Activations Density 0.012%

    No Known Activations