© 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. 20311
    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
    åħľ
    -0.08
    assi
    -0.08
     akan
    -0.07
    abbo
    -0.07
    ÃŃveis
    -0.07
    空
    -0.07
    è¯ķè¯ķ
    -0.07
    way
    -0.07
    æĪIJåĬŁ
    -0.06
    .defer
    -0.06
    POSITIVE LOGITS
    ä¸½å¨ľ
    0.09
    linger
    0.08
    ä¸įæĺ¯å¾Ī
    0.08
    çļĦä¸įæĺ¯
    0.07
    orien
    0.07
    &,
    0.07
    _clr
    0.07
    ä»Ģä¹Īåij¢
    0.07
    nero
    0.07
    incy
    0.07
    Activations Density 0.000%

    No Known Activations