© 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. 32450
    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
    ä¸İéĿŀ
    -0.08
    chan
    -0.08
    åħ¸
    -0.07
    รี
    -0.07
    uco
    -0.07
     föl
    -0.07
    ovid
    -0.06
     ׳×Ļת
    -0.06
    uÅŁ
    -0.06
    ë¥Ń
    -0.06
    POSITIVE LOGITS
    è²Ķ
    0.07
    plice
    0.07
    kj
    0.07
     amet
    0.07
    obet
    0.07
    å±
    0.06
    æī©å±ķèµĦæĸĻ
    0.06
    isman
    0.06
    elt
    0.06
    erves
    0.06
    Activations Density 0.000%

    No Known Activations