© 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. 38449
    Prev
    Next
    INDEX
    Explanations

    sending or outputting data/packets

    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
    ITER
    -0.08
    kst
    -0.08
    TestFixture
    -0.08
    kson
    -0.08
    ç»´åħĭ
    -0.08
    -Ta
    -0.08
    -dismiss
    -0.07
    gau
    -0.07
    indari
    -0.07
    &S
    -0.07
    POSITIVE LOGITS
    åĬłå·¥
    0.10
     output
    0.10
     ampl
    0.09
     outgoing
    0.09
    è¾ĵåĩº
    0.08
    çļĦè¾ĵåĩº
    0.08
    -output
    0.08
     Ampl
    0.08
     Output
    0.08
     processed
    0.08
    Activations Density 0.086%

    No Known Activations