© 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. 25290
    Prev
    Next
    INDEX
    Explanations

    languages and character types

    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
    没æľī被
    -0.07
    没æľīåľ¨
    -0.07
     unf
    -0.07
    kena
    -0.07
    æĭīæīĭ
    -0.07
    á»ijn
    -0.07
    æĭįæĭį
    -0.07
    Unnamed
    -0.07
    мина
    -0.07
    Viewport
    -0.07
    POSITIVE LOGITS
    æĽ´å¥½
    0.07
    adel
    0.07
    çħ¦
    0.07
    uese
    0.07
    æī¼
    0.06
    æ·±åħ¥è´¯å½»
    0.06
    _CI
    0.06
    æĽ´ä½³
    0.06
    abut
    0.06
    大æĦı
    0.06
    Activations Density 0.001%

    No Known Activations