© 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. 20407
    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
    æŃ£æľ¬
    -0.08
     nuru
    -0.08
    isex
    -0.08
    å¾Ĺæ°´
    -0.08
    ROTO
    -0.08
    .'&
    -0.07
    åĪĩå®ŀæıIJé«ĺ
    -0.07
    igators
    -0.07
    бек
    -0.07
    hread
    -0.07
    POSITIVE LOGITS
    æŁIJç§į
    0.09
    æŁIJäºĽ
    0.09
     certain
    0.08
     something
    0.08
     certaines
    0.08
    /
    0.07
    ä¹ĭç±»
    0.07
    something
    0.07
    æľįåĬ¡çŃī
    0.06
    à¸ļาà¸ĩà¸Ńยà¹Īาà¸ĩ
    0.06
    Activations Density 0.000%

    No Known Activations