© 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. 63578
    Prev
    Next
    INDEX
    Explanations

    strategy and code punctuation

    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
    åĨħ容æıIJä¾Ľæĸ¹
    -0.09
    jec
    -0.09
    ename
    -0.09
    à¸ĵะ
    -0.09
    egot
    -0.08
    deps
    -0.08
    uard
    -0.08
    asename
    -0.08
    habi
    -0.08
    é»Ħæ¢ħ
    -0.08
    POSITIVE LOGITS
    å¼ıçļĦ
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    /'
    0.07
    å¼ıä¸Ń
    0.07
    å¼ı
    0.07
    åħ¶ä¸Ń
    0.07
    æł·çļĦ
    0.07
    俱ä¹IJéĥ¨
    0.06
    å½¢å¼ıçļĦ
    0.06
    Activations Density 0.223%

    No Known Activations