© 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. 10776
    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
    gie
    -0.08
    è®¤çľŁåģļ好
    -0.08
    å¼ĵ
    -0.08
    uis
    -0.08
    ãĢĴ
    -0.07
    éĻ·
    -0.07
    apro
    -0.07
     Äijục
    -0.07
    åľ¨ä¸Ģå®ļ
    -0.07
    popular
    -0.07
    POSITIVE LOGITS
    imizer
    0.08
    idora
    0.07
    ×ķ×ij×Ķ
    0.07
    istrator
    0.07
    å°±æĭ¿
    0.06
    ackbar
    0.06
    althy
    0.06
    heets
    0.06
     mentor
    0.06
     mirror
    0.06
    Activations Density 0.000%

    No Known Activations