© 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. 32269
    Prev
    Next
    INDEX
    Explanations

    code tags and special characters

    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
    elih
    -0.07
    /commons
    -0.07
    åıĪéģĵ
    -0.06
    γε
    -0.06
    äng
    -0.06
    è¿ĻéĩĮ
    -0.06
    èĻ½å°ı
    -0.06
    ses
    -0.06
    è¿ŀçݯ
    -0.06
    ervlet
    -0.06
    POSITIVE LOGITS
    uble
    0.08
    -Origin
    0.07
    ä¿ĿæĬ¤èĩªå·±çļĦ
    0.07
    ç¢į
    0.07
    以为æĺ¯
    0.07
    åĬ³åĬ¨æ³ķ
    0.07
    ä¸ļåĬ¡ç´łè´¨
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    emon
    0.07
    Paragraph
    0.07
    Activations Density 0.001%

    No Known Activations