© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54927
    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
    Negative Logits
    пил
    -0.08
    еÑģÑĤа
    -0.07
    anga
    -0.07
    ills
    -0.06
    å»ī
    -0.06
    为åģļ好
    -0.06
    ÑĥÑĢг
    -0.06
    åĢĴ
    -0.06
    aska
    -0.06
    为äºĨæĸ¹ä¾¿
    -0.06
    POSITIVE LOGITS
    èĩªæĭħ
    0.07
    undle
    0.07
    \-
    0.07
    eced
    0.07
    âĢIJ
    0.06
    ä¹ĭæľ¬
    0.06
    shima
    0.06
    Õ¸Õ²
    0.06
    å°ıæľī
    0.06
    bourg
    0.06
    Activations Density 0.000%

    No Known Activations