© 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. 2663
    Prev
    Next
    INDEX
    Explanations

    chemical notation

    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
    Į¨
    -0.21
     QFont
    -0.19
    pivot
    -0.19
    éĽĨè£ħ
    -0.18
    å¾ĹäºĨ
    -0.18
    æī¿æİ¥
    -0.18
    æģ¯æģ¯
    -0.18
    没æľīæĥ³åĪ°
    -0.18
    身边çļĦ
    -0.18
    ç£ķ
    -0.18
    POSITIVE LOGITS
    oulos
    0.27
    :numel
    0.24
    forgettable
    0.23
    stä
    0.23
    bucks
    0.22
    oard
    0.22
    iage
    0.22
    resher
    0.22
    >({
    0.22
    byter
    0.21
    Activations Density 0.072%

    No Known Activations