© 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. 29305
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases and titles

    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
    ĥĿ
    -0.06
    æľįåĬ¡åĨħ容
    -0.06
    Warnings
    -0.06
     bun
    -0.06
    åŃ¦ä¹łè´¯å½»
    -0.06
    allery
    -0.06
    ľ
    -0.06
    好æĸĩ
    -0.06
    itz
    -0.06
    ä¸įåı¯æĢĿè®®
    -0.06
    POSITIVE LOGITS
    heiro
    0.08
    irikan
    0.07
    skap
    0.07
    retty
    0.07
    åŃĹ
    0.07
    kens
    0.07
    &amp
    0.07
    otar
    0.07
    æĶ¶èĹıæľ¬ç«Ļ
    0.07
    isikan
    0.07
    Activations Density 0.017%

    No Known Activations