© 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. 25922
    Prev
    Next
    INDEX
    Explanations

    uncertainty and verification

    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
    classified
    -0.08
     Either
    -0.07
    çİ
    -0.07
    大æĪ·
    -0.07
    åĩºå±Ģ
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.06
    Either
    -0.06
     chán
    -0.06
    ÑĤам
    -0.06
    Meanwhile
    -0.06
    POSITIVE LOGITS
    æľªå¿ħ
    0.12
    ä¸įä¸Ģå®ļ
    0.11
     ë³´ìŀ¥
    0.10
    åīįæıIJæĺ¯
    0.09
    ä¸įä¸Ģå®ļæĺ¯
    0.09
     garant
    0.09
    åīįæıIJ
    0.09
    ä¿Ŀ証
    0.08
     guarantee
    0.08
    è¿ĺæĺ¯æľīäºĽ
    0.08
    Activations Density 0.009%

    No Known Activations