© 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. 1546
    Prev
    Next
    INDEX
    Explanations

    threw right / hand in / organ from

    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
     Sle
    -0.08
     تعب
    -0.08
    ectors
    -0.07
    ToFront
    -0.07
     fetched
    -0.07
    سÙĦÙħ
    -0.07
    åłª
    -0.07
    cly
    -0.07
    æĻ´å¤©
    -0.07
    æĪĸ以
    -0.07
    POSITIVE LOGITS
    çļĦæĺ¯
    0.08
    çļĦä¸įæĺ¯
    0.07
    wal
    0.07
     padi
    0.06
    rix
    0.06
    çļĦæĺ¯ä»Ģä¹Ī
    0.06
    bito
    0.06
    ickest
    0.06
    Docs
    0.06
    çļĦéĥ½æĺ¯
    0.06
    Activations Density 0.031%

    No Known Activations