© 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. 7337
    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
    ubro
    -0.07
    ouce
    -0.07
    ('.'
    -0.07
    amo
    -0.07
    ÏĨι
    -0.07
    elok
    -0.07
    unek
    -0.06
     sud
    -0.06
    æ£ĢæŁ¥å·¥ä½ľ
    -0.06
     boc
    -0.06
    POSITIVE LOGITS
    eteria
    0.08
    uiltin
    0.07
    .Absolute
    0.07
    é¢Ħå¤ĩåħļåijĺ
    0.07
     ÑĦÑĢак
    0.07
     Anyway
    0.07
    ustin
    0.06
    \Active
    0.06
    adrid
    0.06
    summary
    0.06
    Activations Density 0.000%

    No Known Activations