© 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. 60067
    Prev
    Next
    INDEX
    Explanations

    mathematical indices and variables

    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
    è¿ĺ好
    -0.07
     Guilherme
    -0.07
    æľīæĥħ
    -0.07
    -Language
    -0.07
    ä¹ĭåIJİåĨį
    -0.07
    æĥħè°Ĭ
    -0.06
    æĮºèĥ¸
    -0.06
     timed
    -0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.06
    burg
    -0.06
    POSITIVE LOGITS
    ifter
    0.07
    æĵ¦äºĨ
    0.07
    åĪĽå»ºæ´»åĬ¨
    0.07
    _arrays
    0.06
    WithOptions
    0.06
    _runner
    0.06
     vert
    0.06
    itters
    0.06
    avigator
    0.06
    对éĶĻ
    0.06
    Activations Density 0.015%

    No Known Activations