© 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. 23515
    Prev
    Next
    INDEX
    Explanations

    research translation to practice

    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
    åĪĽéĢłä¸Ģ个
    -0.08
    лÑĮÑĤи
    -0.07
     formally
    -0.07
    -created
    -0.07
    arani
    -0.07
    ehen
    -0.07
    èĩªå¤ĩ
    -0.07
    åĽłåħ¬
    -0.07
    isial
    -0.07
    _seed
    -0.06
    POSITIVE LOGITS
     practical
    0.17
     Practical
    0.15
    å®ŀçĶ¨
    0.14
    å®ŀçĶ¨æĢ§
    0.14
    å®ŀçĶ¨çļĦ
    0.13
     пÑĢак
    0.13
     praktis
    0.13
     actionable
    0.12
    實çĶ¨
    0.12
     praktische
    0.12
    Activations Density 0.126%

    No Known Activations