© 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. 37892
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    orsch
    -0.08
    §
    -0.07
    ollo
    -0.07
    该åĮº
    -0.07
    utr
    -0.07
    aleb
    -0.07
    flo
    -0.06
    agner
    -0.06
    ouve
    -0.06
    weeney
    -0.06
    POSITIVE LOGITS
    łĢ
    0.08
    äºĨä¸ĢåĪĩ
    0.08
    æ¨Ł
    0.08
    ArrayType
    0.08
     sequentially
    0.07
    éļĶ天
    0.07
     seper
    0.07
    åºı
    0.07
    ä¾Ŀ次
    0.07
     деÑĢе
    0.07
    Activations Density 0.007%

    No Known Activations