© 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. 503
    Prev
    Next
    INDEX
    Explanations

    programming attributes

    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
     cerco
    -0.23
     suce
    -0.23
     délai
    -0.23
     culo
    -0.22
     siti
    -0.22
    uh
    -0.20
    ä½Ĩä¸įéĻIJ
    -0.19
     multer
    -0.19
    女æĺŁ
    -0.19
     PhpStorm
    -0.19
    POSITIVE LOGITS
    /Internal
    0.27
    ',//
    0.27
    :<?
    0.26
    }'",
    0.26
    ÂĢÂĻ
    0.25
    CodeAt
    0.25
    ;if
    0.24
    ,System
    0.24
     mies
    0.24
     èĩªåĬ¨çĶŁæĪIJ
    0.24
    Activations Density 1.340%

    No Known Activations