© 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. 61449
    Prev
    Next
    INDEX
    Explanations

    return sum or result

    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
    orgen
    -0.06
    åĿļå®Īå²Ĺä½į
    -0.06
     N
    -0.06
     bych
    -0.06
    nid
    -0.06
    伤
    -0.06
     II
    -0.06
     small
    -0.05
     on
    -0.05
    NI
    -0.05
    POSITIVE LOGITS
    verket
    0.08
    WithTag
    0.08
    immen
    0.08
    éĿŀå¾Ĺ
    0.08
    ĺ
    0.07
    æĤ¨åı¯èĥ½
    0.07
    å¾·åįİ
    0.07
    enje
    0.07
    ç«ĭ交
    0.07
    ç´«
    0.07
    Activations Density 0.002%

    No Known Activations