© 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. 65420
    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
    hoven
    -0.09
    ÙĪادÙĩ
    -0.08
    ÙĪدÙĩ
    -0.08
    wing
    -0.08
    ç¼¥
    -0.08
    usif
    -0.08
    好å¿ĥæĥħ
    -0.08
    nton
    -0.08
    нÑĤо
    -0.08
    漪
    -0.08
    POSITIVE LOGITS
     er
    0.08
    irit
    0.06
    éĢļè¿ĩç½ij绾
    0.06
    åĢŁ
    0.06
    ç§ijæĸ¯
    0.06
     im
    0.06
    gil
    0.06
    人æĥħ
    0.06
     bor
    0.06
     mid
    0.06
    Activations Density 0.000%

    No Known Activations