© 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. 43685
    Prev
    Next
    INDEX
    Explanations

    construction company or industry

    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
    幽幽
    -0.07
    åĮ£
    -0.07
    usser
    -0.07
    é¦ĨèĹı
    -0.06
    ologue
    -0.06
    å¹½
    -0.06
    ymm
    -0.06
    æ©Ħ
    -0.06
    沦
    -0.06
    ï¸İ
    -0.06
    POSITIVE LOGITS
    çļĦæĸ½å·¥
    0.11
    å®Įå·¥
    0.10
    åľ¨æĸ½å·¥
    0.10
    竣工
    0.09
    ç«£
    0.09
    å·¥æľŁ
    0.09
     ÑģÑĤÑĢоиÑĤелÑĮ
    0.09
    éĴ¢çŃĭ
    0.09
    manship
    0.09
    æĢ»æī¿åĮħ
    0.09
    Activations Density 0.082%

    No Known Activations