© 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. 20910
    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
    ãĥªãĤª
    -0.08
    _unused
    -0.07
    æµģè¿ŀ
    -0.07
    ri
    -0.07
    Ķ
    -0.07
    verse
    -0.07
    anzas
    -0.07
     rij
    -0.07
    åģ¿
    -0.06
    ignore
    -0.06
    POSITIVE LOGITS
     Nay
    0.07
    PKG
    0.07
    åĴĭ
    0.07
    çŀ¬æģ¯
    0.07
    arring
    0.07
    麽
    0.07
    nay
    0.07
    ä½¼
    0.07
    اراÙĨ
    0.07
    metic
    0.06
    Activations Density 0.000%

    No Known Activations