© 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. 34225
    Prev
    Next
    INDEX
    Explanations

    state of being silent

    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
    yar
    -0.08
    manship
    -0.08
    asaki
    -0.08
    /client
    -0.08
     ÑģложноÑģÑĤи
    -0.08
    Äħtek
    -0.07
    亲æ°ij
    -0.07
    ially
    -0.07
    hias
    -0.07
    åħ¬èĭ±
    -0.07
    POSITIVE LOGITS
    ä¸įè¯Ń
    0.15
    æĹłå£°
    0.12
    éĿĻçļĦ
    0.11
    silent
    0.11
    é»ĺé»ĺçļĦ
    0.11
     lặng
    0.11
     Silent
    0.10
    Sil
    0.10
    æ²īé»ĺ
    0.10
    à¹Ģà¸ĩียà¸ļ
    0.10
    Activations Density 0.044%

    No Known Activations