© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29951
    Prev
    Next
    INDEX
    Explanations

    total count or sum

    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
    atical
    -0.08
    atically
    -0.08
    nitz
    -0.08
    atica
    -0.08
    zion
    -0.07
    à¹Ī
    -0.07
    æĢ»é¢Ŀ为
    -0.07
    mailto
    -0.07
    kop
    -0.07
    ette
    -0.07
    POSITIVE LOGITS
    itarian
    0.12
    deauna
    0.10
    ting
    0.10
    enance
    0.09
    warzys
    0.09
    itario
    0.08
    izers
    0.08
    mente
    0.08
    ayout
    0.08
    ŀ
    0.08
    Activations Density 0.031%

    No Known Activations