© 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. 64282
    Prev
    Next
    INDEX
    Explanations

    consider mathematical or scientific concepts

    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
    è¦ģä¹Īæĺ¯
    -0.07
    charm
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    구ëĬĶ
    -0.07
     åt
    -0.07
    orry
    -0.07
     probably
    -0.07
    çļĦè¦ģ
    -0.06
    ::__
    -0.06
    ذا
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģç§į
    0.10
    è¿Ļæł·çļĦä¸Ģ个
    0.09
    ä½ľä¸ºåĽ½åĨħ
    0.08
    èĢĮè¨Ģ
    0.08
     подÑĢобнее
    0.08
    è¿Ļæł·çļĦæĥħåĨµ
    0.07
    íĸĪëĬĶëį°
    0.07
    è¿Ļæł·ä¸Ģ个
    0.07
    ä½ľä¸º
    0.07
    ãģĹãģ¦ãģ¿ãĤĭãģ¨
    0.07
    Activations Density 0.077%

    No Known Activations