© 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. 26292
    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
    addock
    -0.07
    rieve
    -0.07
    gl
    -0.07
    à¸ģล
    -0.07
    ril
    -0.07
    ä¸į容æĺĵ
    -0.07
    ç¥ŀå±±
    -0.06
    lettes
    -0.06
    zol
    -0.06
    alous
    -0.06
    POSITIVE LOGITS
    æµıè§Ī次æķ°
    0.08
    سخ
    0.08
    jakan
    0.07
    uas
    0.07
     ìŬ
    0.07
    é»ĦçļĦ
    0.07
    رÙĪÙĬ
    0.07
    Compile
    0.07
    åij³çļĦ
    0.07
    æĢ¥æĢ¥
    0.07
    Activations Density 0.000%

    No Known Activations