© 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. 41865
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and code snippets

    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
    ardini
    -0.07
    anan
    -0.07
    使åĩº
    -0.06
    æĥĭ
    -0.06
    æĽ´å¤ļ
    -0.06
    _batches
    -0.06
    åıijçİ°åľ¨
    -0.06
    aths
    -0.06
    رار
    -0.06
    rss
    -0.05
    POSITIVE LOGITS
    ici
    0.08
    elaide
    0.08
    ICI
    0.08
     âĶľâĶĢâĶĢ
    0.08
    lanz
    0.07
    åħ¨æĹ¥åĪ¶
    0.07
    ấy
    0.07
    å¼¹
    0.07
    )ãĢģ
    0.07
    设计åħ¬åı¸
    0.07
    Activations Density 0.238%

    No Known Activations