© 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. 3374
    Prev
    Next
    INDEX
    Explanations

    end

    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
    er
    -0.29
    ing
    -0.25
    i
    -0.25
    a
    -0.25
    ting
    -0.22
    -fw
    -0.21
    ä¸Ń
    -0.19
    ÐŁÐµÑĤеÑĢбÑĥÑĢг
    -0.19
    ed
    -0.19
    æīģ
    -0.19
    POSITIVE LOGITS
     appréci
    0.26
    å¹´ä¹ĭä¹ħ
    0.26
     appré
    0.25
    bellion
    0.25
    thinkable
    0.24
    CLUDED
    0.24
    paralleled
    0.24
    AINED
    0.23
    èģĮä¸ļæĬĢæľ¯
    0.23
    Nguá»ĵn
    0.23
    Activations Density 0.001%

    No Known Activations