© 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. 10209
    Prev
    Next
    INDEX
    Explanations

    reduction, slot, receiving, purchase, related suffixes

    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
    izen
    -0.08
    ROUT
    -0.07
    .persist
    -0.07
    .inspect
    -0.07
    ilio
    -0.07
    OUT
    -0.07
    consistent
    -0.07
    ä¸įç¦ģ
    -0.07
    èĥ
    -0.07
    èī¯
    -0.07
    POSITIVE LOGITS
    ARGS
    0.07
    太åı¤
    0.07
     incoming
    0.07
    ×Ļ×¢
    0.07
    æİ¥åıĹäºĨ
    0.07
    setQuery
    0.07
    æİ¥åıĹçļĦ
    0.07
    utton
    0.07
    ÃŃv
    0.07
    缸åĮ¹éħį
    0.06
    Activations Density 0.003%

    No Known Activations