© 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. 17983
    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
    ascript
    -0.09
    اج
    -0.08
    å°Ķæĸ¯
    -0.08
    ént
    -0.07
    ãĤıãģĸ
    -0.07
    [..
    -0.07
    å®ĥéĤ£
    -0.07
    اÙĪ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    acles
    -0.07
    POSITIVE LOGITS
    consistent
    0.07
     '?'
    0.06
     consistent
    0.06
    èĩªå·±ä¹Ł
    0.06
     only
    0.06
    (?)
    0.06
     requires
    0.06
    æĺ¯èĩªå·±çļĦ
    0.05
    åį¡åľ¨
    0.05
    re
    0.05
    Activations Density 0.019%

    No Known Activations