© 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. 7326
    Prev
    Next
    INDEX
    Explanations

    proper nouns, dates, and technical terms

    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
    çļĦ人æĿ¥è¯´
    -0.08
    ))^
    -0.08
    åıĪèĥ½
    -0.08
    çļĦäººä¹Ł
    -0.08
    ))[
    -0.07
    ])/
    -0.07
    atil
    -0.07
    [âĢ¦]
    -0.07
    ][]
    -0.07
     Ban
    -0.07
    POSITIVE LOGITS
     itself
    0.09
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    æľ¬èº«
    0.07
    èĢĮä¸įæĺ¯
    0.07
     appunto
    0.07
    itat
    0.06
    åħ¶æ¬¡æĺ¯
    0.06
    cc
    0.06
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
     whose
    0.06
    Activations Density 0.067%

    No Known Activations