© 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. 56515
    Prev
    Next
    INDEX
    Explanations

    function argument followed by (

    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
    ng
    -0.07
    ¸
    -0.07
     tact
    -0.07
    éŃı
    -0.06
    éĢıæĺİ
    -0.06
    »
    -0.06
    åıªè§ģ
    -0.06
    èµı
    -0.06
    uf
    -0.06
    .callback
    -0.06
    POSITIVE LOGITS
    tores
    0.08
    ä¸įçł´
    0.08
    ÐijÐł
    0.08
    æĪ¸
    0.08
    å±±æ¹ĸ
    0.07
    aner
    0.07
    okia
    0.07
    jø
    0.07
    utas
    0.07
    raquo
    0.07
    Activations Density 0.017%

    No Known Activations