© 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. 63449
    Prev
    Next
    INDEX
    Explanations

    hemolytic

    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
    .Desc
    -0.08
     area
    -0.06
    lez
    -0.06
    æĺ¯çĶ¨æĿ¥
    -0.06
    док
    -0.05
    .refresh
    -0.05
     interle
    -0.05
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.05
     Kard
    -0.05
    æĭĵ
    -0.05
    POSITIVE LOGITS
    ä¸ĩä¸Ī
    0.09
    à¹īม
    0.08
    PLIT
    0.08
    indsight
    0.08
    udre
    0.08
    ides
    0.08
    itarian
    0.08
    æ¨ĭ
    0.08
    plits
    0.08
    榴
    0.08
    Activations Density 0.002%

    No Known Activations