© 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. 34615
    Prev
    Next
    INDEX
    Explanations

    importance, significance, role

    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
    æį·
    -0.06
     легкой
    -0.06
    uestion
    -0.06
    estina
    -0.06
    è§Ĩ
    -0.06
    ierce
    -0.06
    requ
    -0.06
    elain
    -0.06
    ply
    -0.06
    ä»£æĽ¿
    -0.06
    POSITIVE LOGITS
    ä¸Ģ缮äºĨçĦ¶
    0.10
     ÙĪÙħد
    0.10
    æĺ¯åIJ¦åŃĺåľ¨
    0.10
    æĺ¯ä¸įæĺ¯å¾Ī
    0.10
     trends
    0.09
    åľ¨ä¸įåIJĮ
    0.09
    ä¼ĺåĬ£
    0.08
    æĺ¯åIJ¦éľĢè¦ģ
    0.08
    æĺ¯åIJ¦åħ·æľī
    0.08
    æĺ¯åIJ¦
    0.08
    Activations Density 0.198%

    No Known Activations