© 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. 27517
    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
    Axes
    -0.08
    å¢ĥå¤ĸè¾ĵåħ¥
    -0.08
    issy
    -0.07
    atika
    -0.07
    oload
    -0.07
    çĺŁ
    -0.07
    lund
    -0.07
    ä¿Ŀ驾
    -0.07
    .axes
    -0.07
    umpy
    -0.07
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.08
    вÑĢо
    0.07
    .next
    0.07
    ä¸ĭä¸Ģ
    0.07
     telesc
    0.07
    å¤ļ空
    0.07
    缸éĤ»
    0.07
     ending
    0.06
    å®ŀæĸ½æĦıè§ģ
    0.06
    uku
    0.06
    Activations Density 0.007%

    No Known Activations