© 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. 23118
    Prev
    Next
    INDEX
    Explanations

    observing and recording data

    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
    kev
    -0.07
    æľ¬èº«
    -0.07
    å¢ĥçķĮ
    -0.07
    _ttl
    -0.06
    ä¸įåĴĮ
    -0.06
    çļĦåIJĪæĪIJ
    -0.06
    åħ¶ä»ĸåľ°æĸ¹
    -0.06
     cache
    -0.06
     bound
    -0.06
    ç«ĻåĨħæIJľç´¢
    -0.06
    POSITIVE LOGITS
    æĺ¯åIJ¦æľī
    0.09
     whether
    0.08
    è®°å½ķä¸ĭæĿ¥
    0.08
     hasilnya
    0.08
    æĺ¯åIJ¦ä¸º
    0.08
    whether
    0.08
    è®°å½ķä¸ĭ
    0.07
    Whether
    0.07
    æĺ¯åIJ¦åľ¨
    0.07
    æĺ¯åIJ¦æĺ¯
    0.07
    Activations Density 0.101%

    No Known Activations