© 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. 3087
    Prev
    Next
    INDEX
    Explanations

    common diseases

    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
     best
    -0.25
    æľĢä½³
    -0.24
     лÑĥÑĩ
    -0.23
    æľĢ好çļĦ
    -0.22
     ?>↵↵↵
    -0.21
     meilleurs
    -0.20
    best
    -0.20
    @a
    -0.20
    äºĨ解ä¸Ģä¸ĭ
    -0.19
    çļĦæľĢä½³
    -0.19
    POSITIVE LOGITS
    第äºĮ大
    0.25
    第äºĮç§į
    0.23
    çĥŃæIJľ
    0.22
    ä½ĵèĤ²åľ¨çº¿
    0.22
    ollapsed
    0.21
    dden
    0.21
    inctions
    0.21
    onaut
    0.21
     Após
    0.20
    -Allow
    0.20
    Activations Density 0.886%

    No Known Activations