© 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. 20563
    Prev
    Next
    INDEX
    Explanations

    code keywords with suffixes

    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
    itten
    -0.07
    æľĢè¿ijæĽ´æĸ°
    -0.07
    imore
    -0.06
    erner
    -0.06
    _FOREACH
    -0.06
    reon
    -0.06
    itre
    -0.06
     Somm
    -0.06
    elis
    -0.06
    _THEME
    -0.06
    POSITIVE LOGITS
    åĪĩå°Ķ
    0.08
    amid
    0.08
    ambe
    0.07
    jek
    0.07
    auc
    0.07
    à¥Į
    0.07
    è´·
    0.07
    鼨èĬ±
    0.07
    лаго
    0.07
    aat
    0.06
    Activations Density 0.344%

    No Known Activations