© 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. 50506
    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
    jum
    -0.07
    hir
    -0.07
    åīįä»»
    -0.07
    èĢ½
    -0.07
    èĬľ
    -0.07
    ar
    -0.07
    ä¼Ĺå¿ĹæĪIJ
    -0.06
    fuel
    -0.06
    ames
    -0.06
    _VO
    -0.06
    POSITIVE LOGITS
    太è¡Į
    0.07
    åIJĽåŃIJ
    0.07
    pector
    0.07
    ibri
    0.07
    èĢģå®ŀ
    0.06
    llib
    0.06
    eus
    0.06
    cen
    0.06
    roj
    0.06
    yll
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.