© 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. 51128
    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
    elang
    -0.08
    æ³ķåŃIJ
    -0.08
    æ´»
    -0.07
    alai
    -0.07
    å¨ľ
    -0.07
    endÅij
    -0.07
     ',',
    -0.07
    .Surface
    -0.07
    è°ģçŁ¥éģĵ
    -0.07
    č↵↵
    -0.07
    POSITIVE LOGITS
     Soi
    0.07
    dsm
    0.06
    jord
    0.06
    диÑĤ
    0.06
    udy
    0.06
     total
    0.06
    رع
    0.06
    aira
    0.06
    ussi
    0.06
     Corner
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.