© 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. 57830
    Prev
    Next
    INDEX
    Explanations

    code or technical descriptions

    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
    è®ĵæĤ¨
    -0.08
    让æĤ¨çļĦ
    -0.08
    让æĤ¨
    -0.07
     Anyway
    -0.07
    为æĤ¨çļĦ
    -0.07
    é¥
    -0.07
    è®©ä½łçļĦ
    -0.07
    åı¦è¡ĮéĢļçŁ¥
    -0.07
    оÑĩÑĮ
    -0.07
    ÙĪÙĨد
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮçļĦæĺ¯
    0.09
    çĶ±æѤ
    0.08
    åħ³éĶ®åľ¨äºİ
    0.08
    æĹ¢çĦ¶
    0.08
    éī´äºİ
    0.08
     importantly
    0.08
    èĻ½çĦ¶
    0.07
     although
    0.07
    èĭ¦è¾£
    0.07
    缮æłĩæĺ¯
    0.07
    Activations Density 0.072%

    No Known Activations