© 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. 43558
    Prev
    Next
    INDEX
    Explanations

    punctuation and subsequent words

    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
    大åĴĸ
    -0.07
     appunto
    -0.07
    cz
    -0.06
     types
    -0.06
     اÛĮÙĨÚ©Ùĩ
    -0.06
    顾åIJįæĢĿ
    -0.06
     de
    -0.06
    åľ¨ä»ĸçľĭæĿ¥
    -0.06
     Ease
    -0.06
    .tpl
    -0.06
    POSITIVE LOGITS
    }//
    0.09
    elj
    0.08
    ayani
    0.07
    olat
    0.07
    å¾·éŁ³
    0.07
    æª
    0.07
    æ°´æĺ¯
    0.07
    éĹ®é¢ĺæĿ¥äºĨ
    0.07
    罡
    0.07
    çļĦå¿ĥèĦı
    0.06
    Activations Density 0.001%

    No Known Activations