© 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. 13587
    Prev
    Next
    INDEX
    Explanations

    links containing "Category:"

    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
    ignan
    -0.07
    æ¬
    -0.07
    樱
    -0.07
    \'
    -0.06
    \"
    -0.06
    èĢĮå¤į
    -0.06
    oleh
    -0.06
    ...
    -0.06
    æ²Ī
    -0.06
    çĻ½çİī
    -0.06
    POSITIVE LOGITS
    åħį费注åĨĮ
    0.08
    дем
    0.08
    TRA
    0.08
    å±ķå¼Ģåħ¨æĸĩ
    0.08
    placeholders
    0.07
    eted
    0.07
    ÅŁa
    0.07
    .parse
    0.07
    eting
    0.07
     stub
    0.07
    Activations Density 0.076%

    No Known Activations