© 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. 48715
    Prev
    Next
    INDEX
    Explanations

    background art description

    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
    .pg
    -0.07
    ica
    -0.07
     universally
    -0.07
    ert
    -0.07
    erve
    -0.07
    ir
    -0.07
     Giac
    -0.07
    il
    -0.06
    uesta
    -0.06
    jada
    -0.06
    POSITIVE LOGITS
    ä¸įåĨ³
    0.08
    à¸Ĺาย
    0.08
    decision
    0.08
    çĮľæµĭ
    0.08
    çĮľ
    0.08
     quyết
    0.08
    oky
    0.07
    _guess
    0.07
     Decision
    0.07
    upati
    0.07
    Activations Density 0.005%

    No Known Activations