© 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. 8732
    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
    ilha
    -0.07
     memin
    -0.07
    ä¼ģåĪĴ
    -0.07
     vã
    -0.06
    équ
    -0.06
    以ä¸ĬåѦåİĨ
    -0.06
    åįĥç§ĭ
    -0.06
    以太
    -0.06
    æĢ
    -0.06
     \/
    -0.06
    POSITIVE LOGITS
    oger
    0.08
    imar
    0.08
    imiter
    0.07
    elog
    0.07
    /cop
    0.07
    ouw
    0.07
    ove
    0.07
    Õ¡Öģ
    0.07
    éģ£
    0.07
    ¸
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.