© 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. 55034
    Prev
    Next
    INDEX
    Explanations

    $\mathbb{R}$, $\mathbb{N}$, $\mathbb{Z}$ sets

    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
    anta
    -0.07
    ponsible
    -0.07
    etta
    -0.07
    æĬĬ头
    -0.06
    velle
    -0.06
    åĴĮä¿ĿæĬ¤
    -0.06
    heel
    -0.06
    ÚĺÛĮ
    -0.06
    æ¸
    -0.06
    æĬ¥äºĨ
    -0.06
    POSITIVE LOGITS
    åĴĮä¸ŃåĽ½
    0.08
    ropolit
    0.08
     itself
    0.08
    åĴĮç¾İåĽ½
    0.08
    aland
    0.07
    åĴĮä¸Ĭæµ·
    0.07
    ebes
    0.07
    views
    0.07
    succ
    0.07
    rott
    0.07
    Activations Density 0.030%

    No Known Activations