© 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. 3107
    Prev
    Next
    INDEX
    Explanations

    mixing

    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
    YPD
    -0.27
    uae
    -0.25
    .UIManager
    -0.24
    uxtap
    -0.24
    ERSIST
    -0.24
    __;
    -0.23
     *</
    -0.23
    #ga
    -0.22
    ewis
    -0.22
    .debian
    -0.22
    POSITIVE LOGITS
    æIJħæĭĮ
    0.29
     mixer
    0.27
     mix
    0.26
     mixes
    0.25
     mixing
    0.25
     Mixer
    0.25
     into
    0.24
    æ··åIJĪ
    0.24
    æIJħ
    0.23
     mixture
    0.23
    Activations Density 0.257%

    No Known Activations