© 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. 42514
    Prev
    Next
    INDEX
    Explanations

    arrangement 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
    orno
    -0.10
    ë§ĪìŀIJ
    -0.10
    ectes
    -0.09
    erma
    -0.09
    ward
    -0.09
    avanaugh
    -0.09
    warzys
    -0.09
    ious
    -0.08
    पà¥Ģ
    -0.08
    pline
    -0.08
    POSITIVE LOGITS
    ments
    0.10
    ements
    0.09
    好èĩªå·±çļĦ
    0.09
    妥å½ĵ
    0.08
    ment
    0.08
    amiento
    0.08
    ings
    0.08
    angement
    0.07
    ness
    0.07
    失æݪ
    0.07
    Activations Density 0.036%

    No Known Activations