© 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. 9902
    Prev
    Next
    INDEX
    Explanations

    extend/run directionally

    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
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.09
    urement
    -0.08
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    -0.08
    ä»ĸäºĨ
    -0.08
    被æĬĵ
    -0.08
    æĪijçļĦ人
    -0.08
    她äºĨ
    -0.08
    åIJĦæĸ¹éĿ¢çļĦ
    -0.08
    被åĪ¤
    -0.07
    bery
    -0.07
    POSITIVE LOGITS
    ÑģÑı
    0.10
    äºİ
    0.09
    uate
    0.08
    (ed
    0.08
     into
    0.07
     either
    0.07
     on
    0.07
    ivate
    0.07
     between
    0.07
    è¦ģä¹Ī
    0.07
    Activations Density 0.269%

    No Known Activations