© 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. 15356
    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
    峡
    -0.08
    aps
    -0.07
    ;a
    -0.07
    agy
    -0.07
    aty
    -0.07
    ichever
    -0.07
    getReference
    -0.07
    ;display
    -0.06
    gnore
    -0.06
     Reference
    -0.06
    POSITIVE LOGITS
    nun
    0.06
    ä¸Ģè¯ķ
    0.06
    IW
    0.06
    æĪĸåĽł
    0.06
    äär
    0.06
    جاب
    0.06
    \Lib
    0.06
     Noon
    0.06
     ÙħØŃÙĦ
    0.06
    deo
    0.06
    Activations Density 0.000%

    No Known Activations