© 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. 704
    Prev
    Next
    INDEX
    Explanations

    stage T1 or T2

    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
    Negative Logits
    åİŃ
    -0.08
    èĩ³å°ijè¦ģ
    -0.08
    缺å°ij
    -0.07
    缺
    -0.07
    Minimum
    -0.07
     minimum
    -0.07
    uwe
    -0.07
    minimum
    -0.07
    æľĢä½İ
    -0.07
     Minimum
    -0.07
    POSITIVE LOGITS
    ä¸įè¶ħè¿ĩ
    0.20
    ä¸įèĥ½è¶ħè¿ĩ
    0.16
    à¹Ħมà¹Īà¹Ģà¸ģิà¸Ļ
    0.15
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.15
     <=
    0.13
     âī¤
    0.13
    <=
    0.12
    âī¤
    0.12
    ä¸į大äºİ
    0.11
    MAX
    0.10
    Activations Density 0.111%

    No Known Activations