© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    better yet

    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
    ات
    -0.09
    /of
    -0.08
    ategorized
    -0.08
    cape
    -0.08
    awei
    -0.08
    ught
    -0.08
    ä¸įåIJĮç¨ĭ度
    -0.08
    halat
    -0.08
    ming
    -0.08
    æĹ¢å®ļ
    -0.08
    POSITIVE LOGITS
    lah
    0.08
    èµ·è§ģ
    0.08
    imenti
    0.07
     than
    0.07
    ä¸įä»ħå¦ĤæѤ
    0.07
    æĥħåĨµä¸ĭ
    0.07
    anan
    0.07
    iments
    0.07
    ums
    0.07
    éĩ
    0.07
    Activations Density 0.002%

    No Known Activations