© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58828
    Prev
    Next
    INDEX
    Explanations

    /search/grid

    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
    íķĺìĭľê³ł
    -0.07
    èĥ½éĢļè¿ĩ
    -0.06
    CS
    -0.06
    менÑı
    -0.06
    olly
    -0.06
    èķŃ
    -0.06
    }}{{
    -0.06
    Öģ
    -0.06
    ä¸ĭ表
    -0.06
    å§ijèĭı
    -0.06
    POSITIVE LOGITS
    plr
    0.08
    ئÙĪÙĨ
    0.08
    çĬ¯
    0.07
    /pi
    0.07
    ãĥ©ãĥ³ãĤ¹
    0.07
    utex
    0.07
    éĹ®åĮ»çĶŁ
    0.07
    ضاÙĨ
    0.07
    etti
    0.07
    _decoder
    0.07
    Activations Density 0.001%

    No Known Activations