© 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. 7057
    Prev
    Next
    INDEX
    Explanations

    Ext.define

    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
    ä¸Ģéĥİ
    -0.08
    kul
    -0.07
    bach
    -0.07
    ä¸įåĪĨ
    -0.07
    _LEG
    -0.07
    èĥ½åĬĽçļĦåŁ¹åħ»
    -0.07
    çĿĽ
    -0.07
    icÄĥ
    -0.07
    edula
    -0.07
    bk
    -0.07
    POSITIVE LOGITS
    ayah
    0.07
    æĭįæīĵ
    0.06
    æľ¬æĸĩéĵ¾æİ¥
    0.06
    RAS
    0.06
    peaker
    0.06
    oxel
    0.06
    éĺħè¯»æľ¬æĸĩ
    0.06
    å°Ķ夫
    0.06
    ponse
    0.06
    _helpers
    0.06
    Activations Density 0.004%

    No Known Activations