© 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. 29830
    Prev
    Next
    INDEX
    Explanations

    scientific notation or large/small numbers

    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
    çļĦä¸ĵæłı
    -0.08
    ÐŃÐļ
    -0.08
    ungg
    -0.08
    andu
    -0.08
    ugn
    -0.08
    ارÛĮ
    -0.08
    éia
    -0.07
    æľĪåºķåīį
    -0.07
    ä¸Ģæĸ°
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    POSITIVE LOGITS
    inned
    0.07
    ç³»
    0.06
    çĽĸ
    0.06
    éħĮ
    0.06
    egan
    0.06
    sass
    0.06
    cales
    0.06
     resisted
    0.06
    INESS
    0.06
    edImage
    0.06
    Activations Density 0.005%

    No Known Activations