© 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. 39035
    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¯¹åľ¨
    -0.07
    conom
    -0.07
    icu
    -0.06
    complete
    -0.06
    èĩ³å°ijåľ¨
    -0.06
    衬
    -0.06
    ách
    -0.06
     complete
    -0.06
    ç»ıæµİ
    -0.06
    å¿łè¯ļ
    -0.06
    POSITIVE LOGITS
    大éĢļ
    0.09
    HeaderText
    0.08
    HeaderView
    0.08
    è¡Ķ
    0.08
    é¾Ļ头
    0.08
    ÙIJÙĩ
    0.08
    irão
    0.08
    velle
    0.08
    祺
    0.07
    .showError
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.