© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    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
    incinn
    -0.25
    ornment
    -0.24
    oard
    -0.22
    serter
    -0.22
    chestra
    -0.22
    öyle
    -0.21
    -translate
    -0.21
    /Internal
    -0.21
    .userInteractionEnabled
    -0.20
    .DOM
    -0.20
    POSITIVE LOGITS
    idea
    0.21
    ä¸įåģļ
    0.20
     Wonderland
    0.20
    _SAN
    0.19
     misd
    0.19
    celain
    0.18
    inkel
    0.18
    æĭĬ
    0.18
    ä¸Ģäºĭ
    0.17
    ä¸ĵ项è¡ĮåĬ¨
    0.17
    Activations Density 0.001%

    No Known Activations