© 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. 3046
    Prev
    Next
    INDEX
    Explanations

    ()

    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
    Ỹ
    -0.33
    "<?
    -0.31
     Geli
    -0.29
    /Area
    -0.28
    iasco
    -0.28
    metros
    -0.27
    mue
    -0.27
     Dzi
    -0.26
     GÅĤ
    -0.26
    {id
    -0.26
    POSITIVE LOGITS
    s
    0.26
     spécialisé
    0.25
    à¹Ģหมาะสม
    0.25
    ed
    0.25
     unmist
    0.23
    ting
    0.23
     cazzo
    0.23
     alertController
    0.23
    o
    0.22
     appDelegate
    0.22
    Activations Density 0.107%

    No Known Activations