© 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. 42142
    Prev
    Next
    INDEX
    Explanations

    thermal conductivity

    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
    æĿī
    -0.07
     ÑģбÑĭ
    -0.07
    åįļæł¼
    -0.07
    inga
    -0.07
    åĩºåºĵ
    -0.07
    itzer
    -0.07
    åľ¨æīĢ
    -0.06
    æ·Ģ
    -0.06
    .toObject
    -0.06
     lending
    -0.06
    POSITIVE LOGITS
    éĻ¤äºĨ
    0.14
     via
    0.13
    via
    0.12
     Via
    0.12
     vÃŃa
    0.11
    _via
    0.11
    éĻ¤äºĨæľī
    0.11
    主è¦ģæĺ¯éĢļè¿ĩ
    0.11
    éĻ¤äºĨè¦ģ
    0.11
    ä¸įæĺ¯åĽłä¸º
    0.11
    Activations Density 0.274%

    No Known Activations