© 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. 47562
    Prev
    Next
    INDEX
    Explanations

    **dm docker python Product User Host**

    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
    æľ¬è¯¥
    -0.08
    etheless
    -0.07
    çon
    -0.07
    大ä½ĵ
    -0.07
    åĬĽæīĢèĥ½åıĬ
    -0.07
    ×ij×ķ×ĵ
    -0.07
    epsi
    -0.07
    imal
    -0.07
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
    ãĥªãĤ¨
    -0.07
    POSITIVE LOGITS
    ombe
    0.08
    ãģĦãģĦãģ®ãģĭ
    0.07
    fully
    0.07
    è¿ĻäºĽéĥ½
    0.07
    uario
    0.07
    oin
    0.07
    omorphic
    0.07
    è¿Ļæĺ¯æĪij们
    0.07
    è¿Ļ让
    0.07
    è¿Ļ个æĺ¯
    0.07
    Activations Density 0.007%

    No Known Activations