© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16876
    Prev
    Next
    INDEX
    Explanations

    compare, size, cap

    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
    åĥıä½ł
    -0.08
    _finalize
    -0.08
    .Typed
    -0.08
    emuk
    -0.08
    osit
    -0.08
    olen
    -0.07
    ä¼ĺèĥľ
    -0.07
     ÐŀÑģно
    -0.07
    ãģ«åIJĪãĤıãģĽãģ¦
    -0.07
    èĮĥæĸĩç½ij
    -0.07
    POSITIVE LOGITS
    æ£ĢæŁ¥
    0.11
    æĺ¯åIJ¦ä¼ļ
    0.10
     check
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
     compare
    0.09
     Compare
    0.09
    ä¼ļä¸įä¼ļ
    0.09
    æĺ¯åIJ¦
    0.09
    Compare
    0.09
    æĺ¯åIJ¦åħ·æľī
    0.09
    Activations Density 0.022%

    No Known Activations