© 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. 10211
    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
    ÙĨد
    -0.07
    æn
    -0.07
    åĽ´
    -0.07
    声
    -0.07
    chenk
    -0.07
    æIJŃ
    -0.06
    社
    -0.06
     <![
    -0.06
    élé
    -0.06
    èĩªåı¤
    -0.06
    POSITIVE LOGITS
    etros
    0.07
    çĶŁæ´»ä¼ļ
    0.07
    hado
    0.07
    ETO
    0.07
    λÏī
    0.07
    åĮĸãģĹãģŁ
    0.07
    <Props
    0.07
    æĹłæĦı
    0.07
    `=
    0.07
    IZED
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.