© 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. 1906
    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
    æĹģ
    -0.08
    disc
    -0.07
    æ¢
    -0.07
    åįĩ
    -0.07
    onos
    -0.07
    udel
    -0.07
    ä¸įèµ°
    -0.07
    ä¸ŃæŬ
    -0.06
     bud
    -0.06
    egel
    -0.06
    POSITIVE LOGITS
    è¿Ļ个社ä¼ļ
    0.08
    漩
    0.07
    è¿Ļ次çļĦ
    0.07
    åIJ¹åĵį
    0.07
    æĪĸå°ij
    0.07
    åįģäºĮæĺŁåº§
    0.07
    çĴŀ
    0.07
    ukat
    0.07
    newsletter
    0.07
    以åIJİçļĦ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.