© 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. 47131
    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
    âĢij
    -0.08
    ely
    -0.07
    ogene
    -0.06
    ately
    -0.06
    wl
    -0.06
    åIJ¹é£İ
    -0.06
    è¿ŀäºij
    -0.06
    å°Ĭ
    -0.06
    |#
    -0.06
    king
    -0.06
    POSITIVE LOGITS
    为äºĨèĥ½
    0.09
    umpah
    0.07
    abar
    0.07
    ection
    0.07
    å½ĵäºĭ
    0.07
    eben
    0.07
    -track
    0.07
    filer
    0.07
    产æĿĥæĪ¿
    0.07
    processable
    0.07
    Activations Density 0.000%

    No Known Activations