© 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. 44641
    Prev
    Next
    INDEX
    Explanations

    require statements in code

    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
    ëĤł
    -0.07
    使èĩªå·±çļĦ
    -0.07
    以åıĬ缸åħ³
    -0.07
     ê±°
    -0.06
    eren
    -0.06
    ynamo
    -0.06
     gre
    -0.06
    `
    -0.06
    åĤ¾
    -0.06
    "
    -0.06
    POSITIVE LOGITS
    设
    0.09
    设为
    0.09
    åģĩ
    0.08
    令
    0.08
    ãĥ¼ãĥŀ
    0.07
    ä¸ĭ设
    0.07
    nader
    0.07
    lø
    0.07
    æľīä½į
    0.07
    aname
    0.07
    Activations Density 0.150%

    No Known Activations