© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    sure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    [out
    -0.28
    æŁ¥çľĭ详æĥħ
    -0.26
    Mahon
    -0.24
    *)_
    -0.23
    å¹²äºĭåĪĽä¸ļ
    -0.23
    UART
    -0.22
    Hon
    -0.21
    âĿĮ
    -0.21
     }):
    -0.21
    ;o
    -0.21
    POSITIVE LOGITS
     chắn
    0.36
    PointSize
    0.24
    leness
    0.24
    ormsg
    0.23
    ournaments
    0.23
    endencies
    0.23
    æĹłçĸij
    0.23
    nyder
    0.22
    ulings
    0.22
    agna
    0.22
    Activations Density 0.101%

    No Known Activations