© 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. 48999
    Prev
    Next
    INDEX
    Explanations

    every item or instance

    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
    astery
    -0.08
    lex
    -0.08
    æĢ»é¢Ŀ为
    -0.08
    leo
    -0.08
    ively
    -0.08
    idr
    -0.08
    <|box_end|>
    -0.08
    ezu
    -0.08
    çļĦåIJĦ项
    -0.08
    ylvania
    -0.08
    POSITIVE LOGITS
     conceivable
    0.11
     Äijặn
    0.10
     imaginable
    0.10
    ا
    0.09
    THING
    0.09
     else
    0.09
     possible
    0.08
    گز
    0.08
     تÙĤرÙĬب
    0.08
    féle
    0.08
    Activations Density 0.059%

    No Known Activations