© 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. 31792
    Prev
    Next
    INDEX
    Explanations

    boolean expressions and 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
    çł´æµª
    -0.07
    _DONE
    -0.07
    並以
    -0.07
    cky
    -0.07
    åľ¨æĿŃå·ŀ
    -0.06
    ÑĪли
    -0.06
    éĩĮåħĭ
    -0.06
    xel
    -0.06
    æŁ¥èİ·
    -0.06
    è´§åĪ°
    -0.06
    POSITIVE LOGITS
    æĶĺ
    0.08
    ién
    0.07
    转让
    0.07
    æĪIJå¹´
    0.07
    åĭĴ
    0.06
    éĺ®
    0.06
     herself
    0.06
    ucid
    0.06
    æĢ»æ¯Ķ
    0.06
    aos
    0.06
    Activations Density 0.003%

    No Known Activations