© 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. 64257
    Prev
    Next
    INDEX
    Explanations

    rectifier

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æ°®èĤ¥
    -0.07
    ä¸Ī
    -0.07
    indent
    -0.07
    ucc
    -0.07
    unik
    -0.07
    çIJĨåĮĸ
    -0.07
    راÙħ
    -0.07
     kall
    -0.07
    æł¸
    -0.06
    airie
    -0.06
    POSITIVE LOGITS
    æķ´æµģ
    0.10
    滤波
    0.09
    _converter
    0.08
    vester
    0.08
     converts
    0.08
    /filter
    0.08
     conversion
    0.08
     filtering
    0.08
     converting
    0.07
     Converts
    0.07
    Activations Density 0.007%

    No Known Activations