© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31278
    Prev
    Next
    INDEX
    Explanations

    Ireland

    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
    inkin
    -0.09
     Hadi
    -0.08
    tribu
    -0.08
    رÛĮاÙĨ
    -0.08
    æĪIJåĬŁåIJİåį³åı¯
    -0.08
    lian
    -0.08
    ÙĪØ·
    -0.08
    rops
    -0.08
    irman
    -0.08
    ´Ī
    -0.08
    POSITIVE LOGITS
     Edition
    0.07
    çīĪ
    0.07
    stro
    0.06
    ä¸ĸä¸Ĭ
    0.06
    olg
    0.05
    å´ĸ
    0.05
     (
    0.05
     barrel
    0.05
    aved
    0.05
    ç¯ĵ
    0.05
    Activations Density 0.871%

    No Known Activations