© 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. 16721
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt and variables

    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
    è¿Ļä½į
    -0.07
    稳
    -0.07
    åĽĽä½į
    -0.07
    äºĮä½į
    -0.06
    èĢĮéĻį
    -0.06
    pty
    -0.06
    æĸĮ
    -0.06
    äºĶä½į
    -0.06
    uben
    -0.06
    æ¯ıä½į
    -0.06
    POSITIVE LOGITS
    antino
    0.07
    onga
    0.07
    éĢ¼
    0.06
    ENTI
    0.06
    çģ«çĤ¬
    0.06
    asikan
    0.06
    havn
    0.06
    дона
    0.06
    kong
    0.06
    ughter
    0.06
    Activations Density 0.001%

    No Known Activations