© 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. 1639
    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
    oki
    -0.09
    âĢ¦.
    -0.08
    âĢ¦..
    -0.07
    Âł
    -0.07
    edor
    -0.07
    IJ
    -0.07
    oooo
    -0.07
    âĢ¦
    -0.06
    çļĦæĶ¿çŃĸ
    -0.06
    oon
    -0.06
    POSITIVE LOGITS
    è¯ĨåĪ«äºĮç»´çłģ
    0.09
    stime
    0.08
    _inches
    0.08
    <quote
    0.08
    ypress
    0.07
    .windows
    0.07
    еÑģÑĤи
    0.07
    缸åħ³æݨèįIJ
    0.07
    maf
    0.07
    utm
    0.07
    Activations Density 0.000%

    No Known Activations