© 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. 64941
    Prev
    Next
    INDEX
    Explanations

    descriptive terms followed by specification

    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
    çļĦ人äºĨ
    -0.09
    endio
    -0.09
    人äºĨ
    -0.08
    çľĭå¾Ĺ
    -0.08
    [],
    -0.08
    ä¸įåIJĮç¨ĭ度çļĦ
    -0.08
    å®ĥæīĢ
    -0.08
    æĪijåIJĹ
    -0.08
    çļĦäºĭäºĨ
    -0.07
    åľ¨åĨħçļĦ
    -0.07
    POSITIVE LOGITS
    æ³ķæĺ¯
    0.15
    缮æłĩæĺ¯
    0.15
    çī¹çĤ¹æĺ¯
    0.14
    ä»»åĬ¡æĺ¯
    0.14
    æĸ¹å¼ıæĺ¯
    0.14
    æĸ¹æ³ķæĺ¯
    0.13
    缺çĤ¹æĺ¯
    0.13
    éĹ®é¢ĺæĺ¯
    0.13
    ä¹ĭå¤Ħåľ¨äºİ
    0.13
    ä½ľçĶ¨æĺ¯
    0.13
    Activations Density 0.215%

    No Known Activations