© 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. 30842
    Prev
    Next
    INDEX
    Explanations

    F.3d citation format

    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
     ÐŁÐ¾ÑĢоÑĪенко
    -0.07
    .Commands
    -0.07
     goodies
    -0.07
    &view
    -0.07
    Democrats
    -0.07
    onton
    -0.07
    :error
    -0.07
     Benghazi
    -0.07
    enal
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹ĪæĦıæĢĿ
    0.09
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    ____
    0.08
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
    arity
    0.07
     Klo
    0.07
    æĺ¯ä»Ģä¹Īæł·çļĦ
    0.07
    俱ä¹IJéĥ¨
    0.06
     ______
    0.06
     ï½ľ
    0.06
    Activations Density 8.494%

    No Known Activations