© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26974
    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
    apt
    -0.08
    /apt
    -0.07
    лма
    -0.07
    UCA
    -0.07
    quin
    -0.06
     apt
    -0.06
    .DB
    -0.06
     coup
    -0.06
    ÅŁehir
    -0.06
    LIC
    -0.06
    POSITIVE LOGITS
    ire
    0.07
    OTO
    0.07
    å¼ĢæĴŃ
    0.07
     mieh
    0.07
    preter
    0.07
     Maire
    0.07
    çļĦæŶåĢĻåı¯ä»¥
    0.06
    itol
    0.06
    itut
    0.06
    ful
    0.06
    Activations Density 0.000%

    No Known Activations