© 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. 25662
    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
    immen
    -0.08
     Clash
    -0.07
    Occ
    -0.07
    èĩ´
    -0.07
    enumer
    -0.07
    recht
    -0.07
     predicting
    -0.06
    _CLOSED
    -0.06
    ä¼°ç®Ĺ
    -0.06
    åħ¢åħ¢ä¸ļä¸ļ
    -0.06
    POSITIVE LOGITS
     transformation
    0.13
     transforms
    0.11
     transformations
    0.11
     Transformation
    0.11
     transform
    0.11
    transform
    0.11
    åıĺæį¢
    0.11
     Transform
    0.11
    Transform
    0.10
     transforming
    0.10
    Activations Density 0.011%

    No Known Activations