© 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. 28085
    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
     blah
    -0.08
    reiber
    -0.07
    urette
    -0.07
     ìĪĺë°ĸìĹIJ
    -0.07
    æīĺå°¼
    -0.07
    áŁĦ
    -0.07
     ÑĢаÑģпи
    -0.07
    _MACRO
    -0.06
    .Controller
    -0.06
     Marin
    -0.06
    POSITIVE LOGITS
    singleton
    0.07
    访
    0.07
     Pearce
    0.07
    缨
    0.06
    orthy
    0.06
     Hick
    0.06
    -ing
    0.06
    initializer
    0.06
    _MAY
    0.06
    inggu
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.