© 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. 21222
    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¡t
    -0.08
    åĸľéĹ»
    -0.07
    meister
    -0.07
    ä¸įæİ¥åıĹ
    -0.07
    opup
    -0.07
    ourke
    -0.07
    Ŀ¼
    -0.07
    ogie
    -0.07
    åı°éĿ¢
    -0.07
    åľ°éĽ·
    -0.07
    POSITIVE LOGITS
    _RUN
    0.07
    kah
    0.07
     num
    0.07
    \\/
    0.07
    ç¾İéħĴ
    0.06
    èĭĽ
    0.06
     Hun
    0.06
    ç½Ħ
    0.06
    ystone
    0.06
    /dom
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.