© 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. 24
    Prev
    Next
    INDEX
    Explanations

    k

    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
     Millenn
    -0.43
     Parenthood
    -0.36
    comings
    -0.36
    alleries
    -0.35
    amerate
    -0.34
     Kardash
    -0.34
     Erotic
    -0.34
    hiếu
    -0.34
    orgeous
    -0.34
     Wrest
    -0.34
    POSITIVE LOGITS
    elsey
    0.46
    itchens
    0.39
    rypton
    0.32
    uhn
    0.32
    etchup
    0.29
    iosk
    0.27
    essler
    0.26
    rieg
    0.25
    CAPE
    0.25
    “Well
    0.24
    Activations Density 2.945%

    No Known Activations