© 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. 49822
    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
    ç«ĭå¿Ĺ
    -0.08
    locs
    -0.07
    iggio
    -0.07
    zni
    -0.07
    cente
    -0.07
    æĸ°ä¸Ģ
    -0.07
    âĢ¦]
    -0.07
    Locations
    -0.07
    trys
    -0.07
    oom
    -0.07
    POSITIVE LOGITS
    ä¹Łåı«
    0.12
    åıĪ称
    0.11
    ä¹Łç§°
    0.10
    åıĪåı«
    0.10
    ä¹Łç§°ä¸º
    0.09
     refers
    0.09
    åıĪ称为
    0.08
    åıĪåIJį
    0.08
    顾åIJįæĢĿä¹ī
    0.08
    æĮĩçļĦæĺ¯
    0.08
    Activations Density 0.000%

    No Known Activations