© 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. 60854
    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
    atot
    -0.07
    euw
    -0.07
    atriz
    -0.07
    ilyn
    -0.07
    iou
    -0.07
    yra
    -0.07
    æĺŁæłĩ
    -0.07
    styleType
    -0.07
    ontos
    -0.07
    eson
    -0.07
    POSITIVE LOGITS
    æĺ¯æĥ³
    0.07
    ledge
    0.07
    éľĸ
    0.07
    /main
    0.07
    mour
    0.07
    å¹¢
    0.07
    vidia
    0.06
    ÑĨева
    0.06
    RC
    0.06
     version
    0.06
    Activations Density 0.000%

    No Known Activations