© 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. 3602
    Prev
    Next
    INDEX
    Explanations

    closing bracket

    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
    ly
    -0.12
    اء
    -0.11
    à¦ĩ
    -0.11
    ../../../
    -0.11
    ially
    -0.10
    åĮªæµħ
    -0.10
    ting
    -0.10
    ation
    -0.10
    à§įত
    -0.10
    à§įন
    -0.10
    POSITIVE LOGITS
    s
    0.17
    ات
    0.13
    Ñĭ
    0.11
    ãĥ¥
    0.10
    ska
    0.10
    siz
    0.10
    sver
    0.09
    schild
    0.09
    sung
    0.09
    sök
    0.09
    Activations Density 0.188%

    No Known Activations