© 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. 16471
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and statistical mechanics

    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
    æıIJåįĩèĩªå·±
    -0.08
    ä¸įæĶ¾å¼ĥ
    -0.08
    ifu
    -0.08
    Ø·ÙĦا
    -0.08
    æĸ½å·¥è¿Ľåº¦
    -0.08
    åŀĭå¼ı
    -0.07
    ammers
    -0.07
    angk
    -0.07
    æľºæ¢°åĪ¶éĢłæľīéĻIJåħ¬åı¸
    -0.07
    zien
    -0.07
    POSITIVE LOGITS
     fluctuations
    0.08
     temperature
    0.08
    Entropy
    0.08
    温度
    0.08
    _entropy
    0.08
    åħĨ
    0.08
    Temperature
    0.08
     Temperature
    0.08
    åī¯æľ¬
    0.07
    igas
    0.07
    Activations Density 0.005%

    No Known Activations