© 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. 29460
    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
    å¹³æ»ij
    -0.07
    èݲ
    -0.06
     Smooth
    -0.06
    icot
    -0.06
    ials
    -0.06
    æľ¬æ¬¡æ´»åĬ¨
    -0.06
    á»ijng
    -0.06
    amerate
    -0.06
     Fuk
    -0.06
     Seed
    -0.06
    POSITIVE LOGITS
    Ïĥμ
    0.08
    omma
    0.08
    edia
    0.07
    insta
    0.07
    μμ
    0.07
    ilien
    0.07
     Doming
    0.07
    orno
    0.07
    пиÑĤа
    0.07
    iam
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.