© 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. 63727
    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
    缮ä¸Ń
    -0.07
    足
    -0.07
    itom
    -0.07
    anged
    -0.07
    adoo
    -0.06
    awesome
    -0.06
     olho
    -0.06
    被æī§è¡Į
    -0.06
    ciano
    -0.06
    .builders
    -0.06
    POSITIVE LOGITS
    åŃķå¦ĩ
    0.08
    请çĻ»å½ķ
    0.07
    ilogy
    0.07
    ä¸ĢæıIJ
    0.07
    æĹłæĿ¡ä»¶
    0.07
    æ©
    0.07
    é¹Ń
    0.06
    eme
    0.06
    endan
    0.06
    åħ¨è·¯æ®µ
    0.06
    Activations Density 0.000%

    No Known Activations