© 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. 13860
    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
    ering
    -0.10
    åĪĨ许
    -0.10
    åħ¶èº«
    -0.09
    edly
    -0.08
    åħ¶åľ¨
    -0.08
    اÛĮØ´
    -0.08
    engah
    -0.08
    åħ¶ä¸»è¦ģ
    -0.08
    atters
    -0.08
    aeda
    -0.08
    POSITIVE LOGITS
    çļĦ
    0.08
    æĸ¹éĿ¢
    0.07
    vs
    0.07
    æľ¬èº«
    0.07
     _,
    0.06
    æīĢåľ¨
    0.06
    nya
    0.06
    d
    0.06
    æıIJä¾Ľ
    0.06
    å®ļçĦ¶
    0.06
    Activations Density 0.000%

    No Known Activations