© 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. 42986
    Prev
    Next
    INDEX
    Explanations

    so conclusion / summary

    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
    æĪĸéĥ¨åĪĨ
    -0.08
    缸éļı
    -0.08
    æĪĸå¤ļ个
    -0.07
     tầm
    -0.07
    天河
    -0.07
    -runner
    -0.07
    ogg
    -0.07
    kof
    -0.07
     ведÑĮ
    -0.07
    Å¡kai
    -0.07
    POSITIVE LOGITS
    æĺ§
    0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.08
     conclusion
    0.07
     summary
    0.07
    ersp
    0.07
    æĢ»ç»ĵ
    0.07
     conclude
    0.06
     concludes
    0.06
    agnet
    0.06
    æķ´çIJĨ
    0.06
    Activations Density 0.002%

    No Known Activations