© 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. 41310
    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¥Ĺ
    -0.07
    ä¸Ģå±Ĥ
    -0.07
    åĭ¿
    -0.07
     McN
    -0.07
    ncmp
    -0.06
    à¸ļุรี
    -0.06
    å®ļ
    -0.06
    бина
    -0.06
     Caucus
    -0.06
    ä¸įå¾Ĺ
    -0.06
    POSITIVE LOGITS
    izzie
    0.07
    ansch
    0.07
    纾
    0.07
    cak
    0.07
    tz
    0.07
     épis
    0.07
    cac
    0.07
    ynchronously
    0.07
    ĺ
    0.07
    äºĭ實
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.