© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    entropy calculation metrics

    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
    èµģ
    -0.07
    athers
    -0.07
    éĺ¿å§Ĩæĸ¯
    -0.07
     Kremlin
    -0.07
    heb
    -0.07
    Compr
    -0.07
    ipse
    -0.07
     Merke
    -0.07
    angkatan
    -0.07
    INST
    -0.07
    POSITIVE LOGITS
     entropy
    0.09
    entropy
    0.08
    ç
    0.08
    大åı·
    0.07
    uppe
    0.07
     Sandbox
    0.07
     logarith
    0.07
    åıĸåIJij
    0.07
    Entropy
    0.07
    访éĹ®éĩı
    0.07
    Activations Density 0.002%

    No Known Activations