© 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. 46426
    Prev
    Next
    INDEX
    Explanations

    extracting values from sources

    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
    تابعة
    -0.09
    isle
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    fert
    -0.08
    çļĦ
    -0.08
    er
    -0.08
    ìŀİ
    -0.08
    s
    -0.08
    ê¹IJ
    -0.08
    POSITIVE LOGITS
    0.11
    -nil
    0.11
    Ùĭ
    0.10
    hood
    0.10
    IRTUAL
    0.09
    новÑĮ
    0.09
    -added
    0.09
    atican
    0.09
    Ķ
    0.09
    engeance
    0.09
    Activations Density 0.082%

    No Known Activations