© 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. 57287
    Prev
    Next
    INDEX
    Explanations

    generated code or copyright notices

    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
    à§įà¦Ł
    -0.11
    ãģ¾ãģ¾
    -0.11
    å¾Ģ常ä¸Ģæł·
    -0.11
    ยà¹Į
    -0.11
    istics
    -0.11
    Ñħоз
    -0.10
    teid
    -0.10
    âĿ¤ï¸ı
    -0.10
    ìį¨
    -0.10
    ../../../
    -0.10
    POSITIVE LOGITS
    en
    0.09
    人
    0.08
    f
    0.08
    "
    0.08
    ep
    0.08
    е
    0.08
    ald
    0.08
    t
    0.08
    à¸ģาร
    0.08
    <
    0.08
    Activations Density 0.052%

    No Known Activations