© 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. 20652
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions assigning variables

    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
    pit
    -0.07
    èĭĩ
    -0.07
    ÙĪات
    -0.07
    ikir
    -0.06
    asar
    -0.06
    egie
    -0.06
    fäl
    -0.06
    ;$
    -0.06
    <::
    -0.06
    åı¯ä»¥ä¸į
    -0.06
    POSITIVE LOGITS
    unda
    0.07
    åı¤å±ĭ
    0.07
    åŃĺ
    0.07
    еÑħа
    0.07
    elves
    0.07
    æĸĻ
    0.07
     —————————
    0.07
    麽
    0.07
     seed
    0.07
    èĻı
    0.06
    Activations Density 0.031%

    No Known Activations