© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    numeric measurements

    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
    æݨ
    -0.23
    quan
    -0.21
    (""+
    -0.19
    orn
    -0.19
    serter
    -0.18
     ","↵
    -0.18
     Toe
    -0.18
    æĢ¼
    -0.18
     "&#
    -0.17
    arp
    -0.17
    POSITIVE LOGITS
    ±
    0.38
     ±
    0.32
    ';";↵
    0.26
    {↵↵↵
    0.24
     safeg
    0.24
    .);↵
    0.22
    	throws
    0.22
    zcze
    0.21
    -lnd
    0.21
    '=>['
    0.21
    Activations Density 0.351%

    No Known Activations