© 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. 22298
    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
    emailer
    -0.07
    opaque
    -0.06
    æ¦Ĥ
    -0.06
    æĹłæīĢè°ĵ
    -0.06
    bay
    -0.06
    次äºİ
    -0.06
     Revel
    -0.06
    广大çļĦ
    -0.06
    vert
    -0.06
    AffineTransform
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤ¯
    0.08
    ×Ļר×ķת
    0.08
    odik
    0.08
    ONOM
    0.07
    èį
    0.07
    esan
    0.07
    çļĦä¸Ģ声
    0.07
    çļ®ä¹¦
    0.07
    zÃŃ
    0.07
     sout
    0.07
    Activations Density 0.000%

    No Known Activations