© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    NOT or NEVER questions

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    å¤§æ±Ł
    -0.08
    awl
    -0.07
    ::$
    -0.07
    -La
    -0.07
     xô
    -0.07
     xá
    -0.07
     Gò
    -0.07
    éĻ¡
    -0.07
    åıªæľīéĢļè¿ĩ
    -0.07
    POSITIVE LOGITS
    åIJĪä½ľçĶ¨
    0.07
    uarte
    0.07
    sä
    0.07
    heim
    0.07
    æµ®äºij
    0.07
    æĽĻ
    0.07
    peater
    0.07
    kaar
    0.06
    ä¹IJ天
    0.06
    ìĿµ
    0.06
    Activations Density 0.003%

    No Known Activations