© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26806
    Prev
    Next
    INDEX
    Explanations

    age descriptions

    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
    ilde
    -0.08
    Ĺ
    -0.07
    alc
    -0.07
    agne
    -0.07
    oller
    -0.07
    иÑĤай
    -0.07
    onder
    -0.07
    æĿ¿å¼ı
    -0.06
     ÅŁÃ¶yle
    -0.06
    éķ¿åľ¨
    -0.06
    POSITIVE LOGITS
    ç®Ģ书
    0.09
    è°ĥæŁ¥ç»ĵæŀľ
    0.08
     analyses
    0.08
    elaar
    0.08
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.08
    为äºĨèĥ½
    0.08
     comparisons
    0.07
    Figure
    0.07
    ìĿ´ìĥģ
    0.07
     boles
    0.07
    Activations Density 0.269%

    No Known Activations