© 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. 20447
    Prev
    Next
    INDEX
    Explanations

    public class/delegate/method/variable

    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
    Ø©
    -0.08
    ural
    -0.07
    à»Ī
    -0.07
    äºİäºĭ
    -0.07
    åĬŁèĩ£
    -0.07
    ä¹ħä¹ĭ
    -0.07
    åĪ°çı¾åľ¨
    -0.07
    anche
    -0.06
    oczy
    -0.06
    igans
    -0.06
    POSITIVE LOGITS
    an
    0.08
    ÑĮе
    0.08
    (crate
    0.08
    vince
    0.08
    tır
    0.07
    mány
    0.07
    <![
    0.07
    æĻ°
    0.07
    enfant
    0.07
    TECTED
    0.07
    Activations Density 0.082%

    No Known Activations