© 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. 47821
    Prev
    Next
    INDEX
    Explanations

    list format or code syntax

    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
    天å¤ĸ
    -0.09
    yal
    -0.08
    æģ¯
    -0.08
    æĸ°å¤©åľ°
    -0.07
    sob
    -0.07
    edd
    -0.07
    usta
    -0.07
    ä¸īæĸ¹éĿ¢
    -0.07
     holen
    -0.07
    edig
    -0.07
    POSITIVE LOGITS
    ÙĦاغ
    0.07
     describes
    0.06
     Gug
    0.06
    egers
    0.06
    PLIC
    0.06
    ovia
    0.06
    æľ¬äººèº«ä»½è¯ģ
    0.06
     DESCRIPTION
    0.06
    |null
    0.06
    uls
    0.06
    Activations Density 0.001%

    No Known Activations