© 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. 4031
    Prev
    Next
    INDEX
    Explanations

    -ism / -ic suffixes

    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
    é³ĸ
    -0.07
    æĸĽ
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    åħ·æľīä¸Ģå®ļ
    -0.06
    fel
    -0.06
    å©Ĩ
    -0.06
    åĴ¨
    -0.06
    åıĺåĮĸæĥħåĨµ
    -0.06
    iciel
    -0.06
    yre
    -0.06
    POSITIVE LOGITS
    强è°ĥ
    0.10
    åĩºèº«çļĦ
    0.09
    注éĩį
    0.09
     emphasis
    0.09
     principles
    0.09
    -inspired
    0.08
    åŃ¦æ´¾
    0.08
    åĪĻ认为
    0.08
    強調
    0.08
    æ´¾çļĦ
    0.08
    Activations Density 0.037%

    No Known Activations