© 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. 42201
    Prev
    Next
    INDEX
    Explanations

    pidemiology

    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
    a
    -0.07
    ain
    -0.06
    onom
    -0.06
    idem
    -0.06
    mith
    -0.06
    ண
    -0.06
    ap
    -0.06
    m
    -0.06
    ação
    -0.06
    zym
    -0.06
    POSITIVE LOGITS
    isted
    0.09
    ToWorld
    0.09
    vist
    0.08
    treff
    0.08
    erce
    0.08
    TPL
    0.08
    estu
    0.08
    æĺĵåľ°
    0.08
     spiagg
    0.08
    ಷà³įà²Ł
    0.08
    Activations Density 0.002%

    No Known Activations