© 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. 28308
    Prev
    Next
    INDEX
    Explanations

    code assignments or variable declarations

    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
    认
    -0.08
    éħįåIJĪ
    -0.06
    æ¡IJ
    -0.06
    mise
    -0.06
    åıįæĺł
    -0.06
    æ®Ĭ
    -0.06
    çĻ½è¡Ģ
    -0.06
    æĥ³æĸ¹
    -0.06
    Pod
    -0.06
     while
    -0.06
    POSITIVE LOGITS
     Frat
    0.08
    onstr
    0.07
    RIPT
    0.07
    _scripts
    0.07
    ihat
    0.07
    istet
    0.07
    Enumer
    0.07
    ogas
    0.07
    tika
    0.07
    Fcn
    0.07
    Activations Density 0.056%

    No Known Activations