© 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. 49927
    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
    ä¸Ģ举
    -0.08
    ÛĮدÛĮ
    -0.08
    ละ
    -0.07
    好å¿ĥ
    -0.07
    æ¥
    -0.07
    uret
    -0.07
    飬
    -0.07
    íķ©
    -0.07
    é»ijçľ¼åľĪ
    -0.07
    ä»ĩ
    -0.07
    POSITIVE LOGITS
    å¬ī
    0.07
     Crusher
    0.07
    ä¿ĿçķĻ
    0.07
    å±ĬæŶ
    0.07
    ëĭĪëĭ¤
    0.07
     Stamm
    0.07
    wap
    0.06
    å¿ħ
    0.06
    inery
    0.06
    æ¹ĸ滨
    0.06
    Activations Density 0.000%

    No Known Activations