© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    strong coupling and cooperativity parameters

    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
    ander
    -0.08
     remuner
    -0.07
     наÑģ
    -0.07
    衬æīĺ
    -0.07
    ishly
    -0.06
    .ComponentModel
    -0.06
    меÑģÑĤи
    -0.06
    _wr
    -0.06
     ridden
    -0.06
    åĴĮæĪijä¸Ģèµ·
    -0.06
    POSITIVE LOGITS
     strength
    0.09
    强度
    0.09
    è¿ŀæİ¥æľī
    0.08
    iddel
    0.08
    strength
    0.08
     coupling
    0.08
    è¿ŀæİ¥çļĦ
    0.07
    acting
    0.07
    èĢ¦åIJĪ
    0.07
    è¿ŀæİ¥
    0.07
    Activations Density 0.014%

    No Known Activations