© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    add code element

    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
    .HandleFunc
    -0.23
     @{↵
    -0.21
    /Branch
    -0.21
     FactoryBot
    -0.20
    usband
    -0.20
    çīĪæĿĥæīĢæľī
    -0.19
    ilate
    -0.19
    -cols
    -0.19
    -spinner
    -0.18
    leurs
    -0.18
    POSITIVE LOGITS
    .appendChild
    0.39
    .addView
    0.30
    .addWidget
    0.30
    appendChild
    0.30
     addSubview
    0.29
    .addSubview
    0.29
    .addChild
    0.28
    addComponent
    0.27
    .addTo
    0.25
    addTo
    0.25
    Activations Density 0.067%

    No Known Activations