© 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. 10292
    Prev
    Next
    INDEX
    Explanations

    subset of

    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
     lẽ
    -0.10
    istor
    -0.09
    erable
    -0.08
    Ĺı
    -0.08
    baugh
    -0.08
    иÑİ
    -0.08
    enstein
    -0.08
    tır
    -0.08
    eration
    -0.08
    جÙĬÙĨ
    -0.08
    POSITIVE LOGITS
    ed
    0.09
    jenigen
    0.09
    à¥į
    0.08
    ted
    0.08
    tlement
    0.08
    lah
    0.08
    WithError
    0.07
    鸣åĸĩåıŃ
    0.07
    etime
    0.07
     integrante
    0.07
    Activations Density 0.010%

    No Known Activations