© 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. 25533
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
    oline
    -0.09
    ign
    -0.07
    该åĮº
    -0.07
    ignan
    -0.07
    ppv
    -0.06
    æ¼ł
    -0.06
    ç¬ĥ
    -0.06
    æĪ®
    -0.06
     trotz
    -0.06
     exact
    -0.06
    POSITIVE LOGITS
    киÑģло
    0.08
     diras
    0.08
    è¿Ļè¾¹çļĦ
    0.08
     imageSize
    0.08
    ADR
    0.07
    AtPath
    0.07
     Ñģилами
    0.07
    æĢ¡
    0.07
    ESIS
    0.07
    ÑģовеÑģÑĤ
    0.07
    Activations Density 0.002%

    No Known Activations