© 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. 28246
    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
    asar
    -0.08
    eways
    -0.07
    anspruch
    -0.07
    |h
    -0.07
    uber
    -0.07
    æ¯Ķä»ĸ
    -0.07
    elik
    -0.07
    ÃĵS
    -0.07
    ulier
    -0.07
    кали
    -0.07
    POSITIVE LOGITS
    iani
    0.07
    egger
    0.07
    alth
    0.06
    lot
    0.06
    sh
    0.06
    /chart
    0.06
     timeZone
    0.06
    åºļ
    0.06
     shedding
    0.06
    gable
    0.06
    Activations Density 0.000%

    No Known Activations