© 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. 10787
    Prev
    Next
    INDEX
    Explanations

    symmetric, imbalanced, composition, gradient, Cabinet

    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
    举
    -0.07
    IES
    -0.07
    amus
    -0.07
    iders
    -0.07
    èĪī
    -0.07
    wav
    -0.07
    .getSize
    -0.07
    ä¸Ńåħ´
    -0.07
     Zig
    -0.06
    èµĦæł¼è¯ģ书
    -0.06
    POSITIVE LOGITS
     ÙĦصاÙĦØŃ
    0.08
    åIJijçĿĢ
    0.08
     favor
    0.08
     whereby
    0.08
    åħ¶ä¸Ń以
    0.08
     wherein
    0.07
     fav
    0.07
    æľĿçĿĢ
    0.07
     favour
    0.07
     favors
    0.07
    Activations Density 0.051%

    No Known Activations