© 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. 37556
    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
    aid
    -0.07
    armi
    -0.07
    chwitz
    -0.07
    oulos
    -0.07
    è¿ĺ为
    -0.07
    ãģĤãģı
    -0.06
    åŁİä¸Ń
    -0.06
    æľĭ
    -0.06
    æīij
    -0.06
    quo
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.09
    inz
    0.08
    -many
    0.07
    ezi
    0.07
    æŁı
    0.07
    rimon
    0.07
    è¢
    0.06
     fehlt
    0.06
    NULL
    0.06
    äºĶé¢ľåħŃèī²çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations