© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14709
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases indicating judgment

    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
    æī¬éķ¿
    -0.07
    å°½éĩı
    -0.07
    èħ¾
    -0.07
    èĩªå·±åĸľæ¬¢
    -0.06
    yono
    -0.06
    ihn
    -0.06
    odash
    -0.06
     ÙĨظÙħ
    -0.06
    åıijè¯ģ
    -0.06
    TERM
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľä¸º
    0.10
    ç»ĵæŀľæĺ¯
    0.09
    è¿Ļ个æķ°åŃĹ
    0.09
    æľĢç»Ī以
    0.09
    å¾ĹåĩºçļĦ
    0.09
    æľĢç»ĪçļĦ
    0.08
    ç¡®å®ļ为
    0.08
    çŃĶæ¡Ī为
    0.08
    çŃĶæ¡Īæĺ¯
    0.08
    å¾Ĺåĩº
    0.08
    Activations Density 0.006%

    No Known Activations