© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    ulumi
    -0.41
    aternity
    -0.31
    agedList
    -0.30
     TMPro
    -0.30
    sexy
    -0.29
    Hotéis
    -0.28
    âŀ
    -0.28
    /Dk
    -0.28
     Че
    -0.28
    çĸĶ
    -0.27
    POSITIVE LOGITS
    datable
    0.32
    resenter
    0.31
     neighb
    0.30
    aghetti
    0.27
     gratuitement
    0.25
     génér
    0.25
     enthus
    0.24
    variably
    0.23
     lineman
    0.23
    ublish
    0.22
    Activations Density 7.074%

    No Known Activations