© 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. 27031
    Prev
    Next
    INDEX
    Explanations

    sequence like `d,` or `n,`

    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
    æĦ
    -0.07
    consistent
    -0.07
    cons
    -0.06
    æĸ¯å¡Ķ
    -0.06
    flation
    -0.06
    ï¼Ľ
    -0.06
    æIJŀ
    -0.06
    ++;
    -0.06
    æĹ¢çĦ¶
    -0.06
    uran
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.09
    [,
    0.08
    اÛģ
    0.08
    bow
    0.08
    çļĦ話
    0.08
    λή
    0.08
    çļĦ人æĿ¥è¯´
    0.07
     varsa
    0.07
    []):
    0.07
    ichtigkeit
    0.07
    Activations Density 0.007%

    No Known Activations