© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    code patterns

    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
     horm
    -0.26
     enthus
    -0.22
    åĨ·ç¬ij
    -0.22
     oro
    -0.21
     ámb
    -0.21
     BinaryTree
    -0.21
     SqlParameter
    -0.20
     sexuales
    -0.20
    ston
    -0.20
     Trafford
    -0.20
    POSITIVE LOGITS
    :<?
    0.30
    [".
    0.27
    :frame
    0.27
    ifestyles
    0.27
    estroy
    0.26
    ().'/
    0.26
    ictim
    0.26
     createState
    0.26
    ?>>
    0.26
    ngth
    0.25
    Activations Density 0.527%

    No Known Activations