© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    mathematical notation/symbols

    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
    arka
    -0.08
    hung
    -0.08
    _attach
    -0.08
    ilities
    -0.08
    èĢģåŁİ
    -0.07
    綺
    -0.07
    éĴµ
    -0.07
    -END
    -0.07
    éĺħ读åħ¨æĸĩ
    -0.07
    orthy
    -0.07
    POSITIVE LOGITS
    ÃŃn
    0.07
    ay
    0.07
    umon
    0.06
    åŃ£
    0.06
    سط
    0.06
     Sinai
    0.06
    ÑĩÑĥ
    0.06
    ös
    0.06
    alc
    0.06
    oy
    0.06
    Activations Density 0.023%

    No Known Activations