© 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. 22059
    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
    å°Ķæĸ¯
    -0.08
    ugat
    -0.07
    oned
    -0.06
    essler
    -0.06
    estro
    -0.06
    ilus
    -0.06
    ulon
    -0.06
    ped
    -0.06
    udia
    -0.06
    ãĤ¹ãĥĿãĥĥãĥĪ
    -0.06
    POSITIVE LOGITS
    łĢ
    0.07
    inox
    0.07
    é¥
    0.07
    δι
    0.07
    ;$
    0.07
    iva
    0.07
     Isk
    0.06
     Osman
    0.06
    æĿİæĸĩ
    0.06
    robi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.