© 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. 15521
    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
     вм
    -0.08
    举
    -0.07
    iasi
    -0.07
    iong
    -0.07
    Specification
    -0.07
    ikap
    -0.07
    quÃŃ
    -0.07
    INU
    -0.07
    ç½ijç«Ļåľ°åĽ¾
    -0.07
    öst
    -0.07
    POSITIVE LOGITS
     Seymour
    0.07
    ä¸Ĭè¿ĩ
    0.07
    声åIJį
    0.06
    æĢ»å±Ģ
    0.06
    äºĭåīį
    0.06
    rts
    0.06
    opsis
    0.06
    ç±ģ
    0.06
    auc
    0.06
    outed
    0.06
    Activations Density 0.000%

    No Known Activations