© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    spec
    -0.23
    @dynamic
    -0.22
    æĮĩå®ļ
    -0.22
    erguson
    -0.21
     Ä°nternet
    -0.20
    lices
    -0.19
    <Renderer
    -0.19
    specified
    -0.19
    _exempt
    -0.19
    幸
    -0.19
    POSITIVE LOGITS
    adin
    0.21
     guaranteed
    0.21
    æĮĩåIJij
    0.19
    çi
    0.19
    :'',
    0.19
    ETY
    0.19
    éĩĮçļĦ
    0.19
    .IsNotNull
    0.18
    latex
    0.18
    /wiki
    0.18
    Activations Density 0.242%

    No Known Activations