© 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. 14374
    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
    éĹ²
    -0.07
    enaar
    -0.07
    æłĸ
    -0.06
    orce
    -0.06
    ieties
    -0.06
    对å¾ħ
    -0.06
    elingen
    -0.06
    è°ģ
    -0.06
    entic
    -0.06
    iated
    -0.06
    POSITIVE LOGITS
    tang
    0.07
     responsibly
    0.07
    èĮĹ
    0.07
    _pal
    0.07
    æĿĸ
    0.07
    idos
    0.07
    ä½ľèĢħæīĢæľī
    0.07
    ##_
    0.07
    idl
    0.07
    ä¹ĭçİĭ
    0.07
    Activations Density 0.000%

    No Known Activations