© 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. 55364
    Prev
    Next
    INDEX
    Explanations

    beverage industry, cans, container

    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
    bürger
    -0.07
     panen
    -0.07
    Ĺ
    -0.07
    èħĬèĤī
    -0.07
    ständig
    -0.07
    èĤ¥èĤī
    -0.07
    è¡£é£Ł
    -0.07
    .nlm
    -0.07
    累累
    -0.07
    åIJĥæİī
    -0.07
    POSITIVE LOGITS
    饮çĶ¨
    0.10
     beverages
    0.09
    饮æĸĻ
    0.09
     напиÑĤок
    0.09
     напиÑĤков
    0.08
    elain
    0.08
    åIJ¸ç®¡
    0.08
    caffe
    0.08
     напиÑĤки
    0.08
    飲æĸĻ
    0.08
    Activations Density 0.089%

    No Known Activations