© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25086
    Prev
    Next
    INDEX
    Explanations

    Internet, device, hybrid, Solomon, ournal, mitochondria

    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
    æľŃ
    -0.08
    ä¹ĭ书
    -0.07
    blad
    -0.07
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ¯
    -0.07
    æĭĴ
    -0.07
    гаÑĢ
    -0.07
    alp
    -0.07
    éłĥãģ¯
    -0.06
    ÑĤаж
    -0.06
    δÎŃ
    -0.06
    POSITIVE LOGITS
    —a
    0.10
     appunto
    0.09
    è¿Ļæĺ¯ä¸Ģ个
    0.09
    —an
    0.08
     à¸ĭึà¹Īà¸ĩมี
    0.07
    åºĶè¿IJèĢĮçĶŁ
    0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
    —which
    0.07
    è¿Ļæĺ¯ä¸Ģç§į
    0.07
    ody
    0.07
    Activations Density 0.370%

    No Known Activations