© 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. 45331
    Prev
    Next
    INDEX
    Explanations

    mathematical and code elements

    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
    å¿ĥçĹħ
    -0.07
    anea
    -0.07
    Ĺı
    -0.07
    oplevel
    -0.06
    æĺķ
    -0.06
    æ¯ģ
    -0.06
    à¸łà¸±
    -0.06
    olino
    -0.06
    è¿Ļ个éĺ¶æ®µ
    -0.06
    ä¸įåIJĮç¨ĭ度
    -0.06
    POSITIVE LOGITS
    WithName
    0.08
    åľ°çIJĥçļĦ
    0.08
     constants
    0.08
    ifice
    0.08
    à¸Ħุà¹īมà¸Ħรà¸Ńà¸ĩ
    0.08
    uolo
    0.08
    /framework
    0.08
    åģī
    0.07
     universal
    0.07
    常æķ°
    0.07
    Activations Density 0.006%

    No Known Activations