© 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. 27763
    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
    adel
    -0.08
    erie
    -0.08
    iori
    -0.08
    åĪģ
    -0.08
    ewise
    -0.08
    lÄĵ
    -0.07
    ___
    -0.07
    Äĺ
    -0.07
    åĪ«ç¦»
    -0.07
    欢åĸľ
    -0.07
    POSITIVE LOGITS
    çļĦ人们
    0.07
    ow
    0.07
    å½»åºķ
    0.06
    å·¥ä½ľå¼Ģå±ķ
    0.06
    oot
    0.06
    æ±Ģ
    0.06
    æ¬ł
    0.06
    åıĹçĥŃ
    0.06
    .zip
    0.06
    æĺ¯ä¸ĢæĿ¡
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.