© 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. 16493
    Prev
    Next
    INDEX
    Explanations

    Gibbs Free Energy, photons, why

    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
    urd
    -0.09
    %H
    -0.08
     háºŃu
    -0.08
    ugat
    -0.08
    æŃ¥å±¥
    -0.08
    ayet
    -0.08
    sene
    -0.07
    çļĦèī¯å¥½
    -0.07
    OffsetTable
    -0.07
    asty
    -0.07
    POSITIVE LOGITS
    为ä»Ģä¹Īè¦ģ
    0.11
    为ä»Ģä¹Ī
    0.11
     why
    0.10
    为ä½ķ
    0.10
    为åķ¥
    0.10
    çĤºä»Ģ麼
    0.10
    为ä»Ģä¹Īä¸į
    0.10
     Why
    0.09
    æĺİæĺİ
    0.09
    好åĥı
    0.09
    Activations Density 1.399%

    No Known Activations