© 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. 61375
    Prev
    Next
    INDEX
    Explanations

    automotive applications

    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
    {}.
    -0.08
    —but
    -0.07
     {}.
    -0.07
    ++.
    -0.07
    ().
    -0.07
    åĽ¾ä¸º
    -0.07
     ().
    -0.07
    %.
    -0.07
    %).
    -0.07
     "").
    -0.07
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.18
    ,it
    0.16
    çļĦ人æĿ¥è¯´
    0.15
     inilah
    0.14
     ÙģØ¥ÙĨ
    0.13
     _______,
    0.13
     itulah
    0.13
    æĿ¥è¯´
    0.12
     ÙģØ¥ÙĨÙĩ
    0.12
    ä¾Ĩ說
    0.12
    Activations Density 1.055%

    No Known Activations