© 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. 2243
    Prev
    Next
    INDEX
    Explanations

    entropy and complexity

    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
    èĭ«
    -0.08
     umo
    -0.08
    å®īåħ¨åı¯éĿł
    -0.08
    umpl
    -0.08
    æī¿
    -0.08
    ÑĪÑĤÑĥ
    -0.08
    å¦ĤæŀľéľĢè¦ģ
    -0.08
    çļĦæľĢæĸ°
    -0.08
    agul
    -0.08
    檸
    -0.07
    POSITIVE LOGITS
     entropy
    0.10
    æľīæĽ´å¤ļçļĦ
    0.09
     freedom
    0.09
    entropy
    0.09
    Entropy
    0.09
    èĩªçĶ±
    0.09
    ç
    0.08
    èĩªçĶ±åº¦
    0.08
     fewer
    0.08
    çļĦèĩªçĶ±
    0.08
    Activations Density 0.001%

    No Known Activations