© 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. 16983
    Prev
    Next
    INDEX
    Explanations

    muscle or muscles

    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
    符
    -0.09
    æ¼Ĥæµģ
    -0.07
    æĭ·
    -0.07
    åĨĴ
    -0.06
     tainted
    -0.06
     unacceptable
    -0.06
    èĩ´åij½
    -0.06
    æ·ĺæ±°
    -0.06
     fatal
    -0.06
    身ä¸ĸ
    -0.06
    POSITIVE LOGITS
     muscles
    0.12
     muscle
    0.11
    èĤĮèĤī
    0.10
     proprio
    0.10
    åĬĽéĩı
    0.10
    мÑĭÑĪ
    0.09
     Muscle
    0.09
    åĬĽéĩıåĴĮ
    0.09
    åĬĽéĩıçļĦ
    0.09
     muscular
    0.09
    Activations Density 0.048%

    No Known Activations