© 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. 41927
    Prev
    Next
    INDEX
    Explanations

    quieter measures

    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
    åĭĩæķ¢çļĦ
    -0.08
    åĭĩæķ¢
    -0.08
     rough
    -0.08
    ä¸į顾
    -0.08
    åĭĩ
    -0.07
     brave
    -0.07
    èĭ±åĭĩ
    -0.07
    aglio
    -0.07
     pron
    -0.06
    毫ä¸įçĬ¹è±«åľ°
    -0.06
    POSITIVE LOGITS
     subtle
    0.17
     indirect
    0.15
    éĹ´æİ¥
    0.14
     indire
    0.13
    æĹłå£°
    0.13
    åIJ«èĵĦ
    0.13
     quieter
    0.13
     sutil
    0.13
    æĹłå½¢
    0.12
     quietly
    0.12
    Activations Density 0.253%

    No Known Activations