© 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. 48037
    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
    èĢĮä¸Ķæľī
    -0.07
    ENU
    -0.07
    屡
    -0.07
    å±
    -0.07
    èīºæľ¯åѦéĻ¢
    -0.07
    åĺ»
    -0.07
    ساÙĨÙĬ
    -0.07
     vigorous
    -0.07
    unal
    -0.07
    opedia
    -0.07
    POSITIVE LOGITS
     bereit
    0.07
    ’t
    0.06
    abbit
    0.06
    uh
    0.06
    ucch
    0.06
    áĢ¹
    0.06
    zu
    0.06
     Kre
    0.06
     Cure
    0.06
    ijt
    0.06
    Activations Density 0.000%

    No Known Activations