© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 466
    Prev
    Next
    INDEX
    Explanations

    medical and biological

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .heroku
    -0.41
    .IsNullOr
    -0.36
    .za
    -0.33
    [".
    -0.33
     Khá
    -0.32
    @update
    -0.32
    ,application
    -0.32
     jeste
    -0.32
     uda
    -0.32
    âļĹ
    -0.32
    POSITIVE LOGITS
     IntelliJ
    0.21
     citt
    0.21
     appréci
    0.20
    çĶŁäº§æĢ»
    0.19
     advoc
    0.19
     nihil
    0.19
     useMemo
    0.19
     azi
    0.18
    .A
    0.18
     découvert
    0.18
    Activations Density 96.756%

    No Known Activations