© 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. 62269
    Prev
    Next
    INDEX
    Explanations

    legal entities and disciplines

    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
    ÙijÙĬ
    -0.07
    åIJĦ
    -0.06
    /
    -0.06
    (
    -0.06
    ·
    -0.05
    -0.05
    álne
    -0.05
    ãĥĿãĤ¹ãĥĪ
    -0.05
    à§İ
    -0.05
     contingent
    -0.05
    POSITIVE LOGITS
    á»įi
    0.08
    onton
    0.08
    سÙĪب
    0.08
    watan
    0.08
    istrz
    0.07
    æĥ¹äºº
    0.07
    ahui
    0.07
    à¸ļà¸ļ
    0.07
    ahi
    0.07
    arker
    0.07
    Activations Density 0.074%

    No Known Activations