© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17795
    Prev
    Next
    INDEX
    Explanations

    rounding digits

    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
    è¨
    -0.08
     Cousins
    -0.08
    .ordinal
    -0.07
     TOO
    -0.07
    ä¸īæĿ¡
    -0.07
    enberg
    -0.07
    ±
    -0.07
    ë©Ģ
    -0.07
    产åĵģåıĬ
    -0.07
    çŁ¢
    -0.07
    POSITIVE LOGITS
    代
    0.07
    ä¿Ŀéļľæݪæĸ½
    0.06
    lose
    0.06
    æĬĽ
    0.06
    éģĹ
    0.06
    ego
    0.06
     diff
    0.06
    çī¡
    0.06
    é¢Ĩè¢ĸ
    0.06
    _BIN
    0.06
    Activations Density 0.113%

    No Known Activations