© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1367
    Prev
    Next
    INDEX
    Explanations

    beat

    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
     sovere
    -0.28
    oriously
    -0.28
     Dems
    -0.28
    SharedPtr
    -0.27
     oppon
    -0.26
    odore
    -0.25
    owment
    -0.25
     beneficiation
    -0.25
    jumbotron
    -0.23
    ceipt
    -0.23
    POSITIVE LOGITS
    indsay
    0.34
    /Dk
    0.29
    erokee
    0.27
     Gór
    0.27
    oppable
    0.27
    puties
    0.27
    innie
    0.26
    ibold
    0.26
    Grün
    0.26
    moid
    0.26
    Activations Density 7.865%

    No Known Activations