© 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. 23630
    Prev
    Next
    INDEX
    Explanations

    differential calculus notation

    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
    es
    -0.10
    dorf
    -0.07
    en
    -0.07
    chutz
    -0.07
    ein
    -0.06
    is
    -0.06
    dÃŃ
    -0.06
    aldo
    -0.06
    Ñı
    -0.06
    dienst
    -0.06
    POSITIVE LOGITS
    ä¹ĭ以
    0.11
    ownt
    0.11
    ä¸įå®ĮçļĦ
    0.10
    avenport
    0.10
    IALOG
    0.09
    äºĨ好åĩł
    0.09
    uplic
    0.09
    harma
    0.09
    ijkstra
    0.09
    äºĨåĩł
    0.09
    Activations Density 0.004%

    No Known Activations