© 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. 2419
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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
    entrée
    -0.23
    #ga
    -0.22
    kiye
    -0.22
    /Branch
    -0.22
    swire
    -0.22
    meldung
    -0.21
    Friendly
    -0.20
    .InputStreamReader
    -0.20
    alic
    -0.20
    ument
    -0.19
    POSITIVE LOGITS
     )"
    0.22
     Alexandre
    0.20
    pd
    0.19
    ispers
    0.19
    qual
    0.19
    ãİı
    0.19
     OnePlus
    0.18
    éĴ¼
    0.18
    豪å®ħ
    0.18
    :NS
    0.18
    Activations Density 0.013%

    No Known Activations