© 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. 57664
    Prev
    Next
    INDEX
    Explanations

    sports team members

    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
    ↵
    -0.07
    åĪĿèµĽ
    -0.07
    çĥŃéĹ¹éĿŀåĩ¡
    -0.07
    èĥľåĩº
    -0.06
     Nobel
    -0.06
    éĢīæīĭ们
    -0.06
    ãĤ½ãĥ¼ãĥī
    -0.06
     \
    -0.06
    ^
    -0.06
    æ¯ķ
    -0.06
    POSITIVE LOGITS
     talent
    0.10
     rookie
    0.10
     roster
    0.10
    ropp
    0.10
    æĿ¿åĩ³
    0.09
    å¦ĸ
    0.09
     underrated
    0.09
    秣åĢŁ
    0.09
     Legends
    0.09
     preseason
    0.09
    Activations Density 2.960%

    No Known Activations