© 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. 17173
    Prev
    Next
    INDEX
    Explanations

    financial terms and math 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
    mera
    -0.07
    distinct
    -0.07
    è¾Ī
    -0.06
    trib
    -0.06
    tar
    -0.06
    unction
    -0.06
    å¯ĨéĽĨçļĦ
    -0.06
     distinct
    -0.06
    arka
    -0.06
    izo
    -0.06
    POSITIVE LOGITS
    inati
    0.09
    usak
    0.09
     наобоÑĢоÑĤ
    0.09
    åıįä¹ĭ
    0.08
    otos
    0.08
    缸åıįçļĦ
    0.08
    ONSE
    0.08
     sebaliknya
    0.08
    çļĦåıį
    0.08
    åıįåIJij
    0.08
    Activations Density 0.013%

    No Known Activations