© 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. 64367
    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
    ÙĬÙĬر
    -0.08
    antd
    -0.08
    æĺ¥æĦı
    -0.07
    éĿŀåħ¬
    -0.07
     prestazione
    -0.07
     cioc
    -0.07
    úl
    -0.07
    غÙĬ
    -0.07
    #![
    -0.07
    htag
    -0.07
    POSITIVE LOGITS
    åĩºæ²¡
    0.07
     repeat
    0.07
    asha
    0.07
    æIJŀå®ļ
    0.06
    bout
    0.06
    äºĨçĤ¹
    0.06
    ezz
    0.06
    alli
    0.06
    gris
    0.06
    åĽłä¸ºè¿Ļ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.