© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3463
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    regor
    -0.20
    bable
    -0.20
    OfString
    -0.19
    Į¨
    -0.19
    bsite
    -0.19
    onaut
    -0.18
    龸
    -0.18
    ṯ
    -0.18
    Ầ
    -0.18
    peon
    -0.18
    POSITIVE LOGITS
    ðŁĺī
    0.22
    esty
    0.20
    swick
    0.19
    .VAL
    0.19
     bü
    0.19
    -transitional
    0.19
    Informe
    0.19
    ieurs
    0.19
    ordova
    0.19
    åħħ
    0.19
    Activations Density 0.001%

    No Known Activations