© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    medical/technical studies

    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
     ×Ķ×ķ×ĵ
    -0.26
    #echo
    -0.24
    edImage
    -0.22
    _transaksi
    -0.22
    #ac
    -0.21
    glÄħd
    -0.21
    .DialogInterface
    -0.21
    ãĥµ
    -0.21
    å°ı游æĪı
    -0.20
    ç²ľ
    -0.20
    POSITIVE LOGITS
     Dems
    0.26
    -scenes
    0.24
    /legal
    0.22
     PureComponent
    0.21
    bows
    0.21
    kre
    0.21
     kÃŃch
    0.20
     fitte
    0.20
    niest
    0.18
    èµī
    0.18
    Activations Density 0.004%

    No Known Activations