© 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. 59123
    Prev
    Next
    INDEX
    Explanations

    dates and lists

    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
    Negative Logits
    è¦ģçŁ¥éģĵ
    -0.08
    ä¸Ģéĩij
    -0.07
    ูล
    -0.07
     INLINE
    -0.07
    awan
    -0.07
     doing
    -0.07
     ÑħодÑĥ
    -0.06
    ién
    -0.06
     literally
    -0.06
     ÑģовÑģем
    -0.06
    POSITIVE LOGITS
    èĻ½æľī
    0.07
    åĤĻ
    0.07
    illed
    0.07
    ossible
    0.07
    iced
    0.07
    åĪĨæŀIJåıĬ
    0.06
    åħĭæľįåĽ°éļ¾
    0.06
    lina
    0.06
    erged
    0.06
    ioned
    0.06
    Activations Density 0.001%

    No Known Activations