© 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. 60545
    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
    omencl
    -0.07
    a
    -0.07
    entially
    -0.06
    缸åħ³æĥħåĨµ
    -0.06
     Klassen
    -0.06
    纨
    -0.06
    ardin
    -0.06
    æŁĦ
    -0.06
    OfWeek
    -0.06
    hte
    -0.06
    POSITIVE LOGITS
    ized
    0.09
    åĮĸçļĦ
    0.09
    ization
    0.08
    -minded
    0.08
    лÑĥм
    0.08
    isation
    0.08
    оÑĤÑĮ
    0.08
    dden
    0.08
    accio
    0.07
    ities
    0.07
    Activations Density 0.000%

    No Known Activations