© 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. 46850
    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
    èݺ
    -0.07
    elle
    -0.07
    wan
    -0.07
     prov
    -0.07
    à°Łà°¿
    -0.07
    æīįæĺ¯
    -0.07
    æĽ²
    -0.06
     cur
    -0.06
    æĽ´æĺ¾
    -0.06
    avel
    -0.06
    POSITIVE LOGITS
    åıĺæĽ´ä¸º
    0.08
    থা
    0.08
    æıĽ
    0.07
    ãģłãģijãĤĮ
    0.07
    è¡Į家
    0.07
    irme
    0.07
    ugio
    0.07
    пин
    0.07
    пÑĢоÑĩем
    0.07
    顺åĪ©çļĦ
    0.07
    Activations Density 0.000%

    No Known Activations