© 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. 13514
    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
    åĪĨæ¸ħ
    -0.08
    åľŃ
    -0.07
    dung
    -0.07
    brace
    -0.07
    áĢĽáĢ¬
    -0.07
     Jeb
    -0.07
    roman
    -0.07
    chow
    -0.07
    beck
    -0.07
     Allen
    -0.06
    POSITIVE LOGITS
    ä½ļ
    0.07
    å²±
    0.07
    ek
    0.07
    .xhtml
    0.07
    æľĭ
    0.07
    itial
    0.07
    æĥķ
    0.07
    Äĵ
    0.06
    æ·³
    0.06
    ADV
    0.06
    Activations Density 0.000%

    No Known Activations