© 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. 44197
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    .pm
    -0.07
    ijin
    -0.07
    CommandLine
    -0.07
    ULT
    -0.07
    +$
    -0.06
    (routes
    -0.06
    +)\
    -0.06
    (JSON
    -0.06
    åħ¥
    -0.06
     Aut
    -0.06
    POSITIVE LOGITS
    £¼
    0.08
    @email
    0.07
    ÌĢ
    0.07
    ä¸ĢæĶ¹
    0.07
    ihu
    0.07
    æĿ¥çĶµåĴ¨è¯¢
    0.07
    omag
    0.07
    çŁŃåı¥
    0.06
    Ìģ
    0.06
    laise
    0.06
    Activations Density 0.019%

    No Known Activations