© 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. 16544
    Prev
    Next
    INDEX
    Explanations

    br opening block top shaft elong estr acle

    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
     local
    -0.07
    æĵ¦èĤ©
    -0.07
    å»Ĭ
    -0.06
    毯
    -0.06
    çĶ¨å¥½
    -0.06
    åľ°æ¯¯
    -0.06
    udy
    -0.06
    1
    -0.06
    -0.06
    2
    -0.06
    POSITIVE LOGITS
     impugn
    0.09
    æ·±åıĹ广大
    0.09
    rnd
    0.09
    véd
    0.09
     customizable
    0.08
     ÙĤسÙħت
    0.08
    å¹³éĿ¢è®¾è®¡
    0.08
    sembly
    0.08
    身ä½ĵçļĦ
    0.08
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
    Activations Density 0.302%

    No Known Activations