© 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. 2057
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    wn
    -0.06
    ime
    -0.06
    ç»ıèIJ¥æĢ§
    -0.06
    ëĿ¼ìĿ´
    -0.06
    è°·
    -0.06
    adir
    -0.06
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.06
    ider
    -0.06
    ellular
    -0.05
    ä¼ģä¸ļæŁ¥è¯¢
    -0.05
    POSITIVE LOGITS
    大亨
    0.09
    intai
    0.08
    zos
    0.08
     ÎŃγι
    0.07
    oyer
    0.07
    åĪ°èĢģ
    0.07
    udad
    0.07
    .Messaging
    0.07
    ths
    0.07
    æĹłä¸Ĭ
    0.07
    Activations Density 0.000%

    No Known Activations