© 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. 31567
    Prev
    Next
    INDEX
    Explanations

    rich tycoon X

    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
    æľĪ以æĿ¥
    -0.08
    <|box_end|>
    -0.07
    ়
    -0.07
    al
    -0.06
    éķij
    -0.06
    ků
    -0.06
    æľĪèĩ³ä»Ĭ
    -0.06
    etsk
    -0.06
    ftware
    -0.06
    ersiz
    -0.06
    POSITIVE LOGITS
    ãģ¿ãģ®
    0.10
    并èĮĤ
    0.09
    ä»ĭçŁ³
    0.08
    ÙĪرت
    0.08
    ä¸ĢçŃ¹
    0.08
    igor
    0.08
    çijŀæĭī
    0.08
    ê·Ģ
    0.08
    ä¹ĭå®Ŀ
    0.08
    ãģ¿ãģ«
    0.08
    Activations Density 0.061%

    No Known Activations