© 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. 3740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     IonicPage
    -0.22
     Front
    -0.21
    ĵĺ
    -0.21
    èĥį
    -0.20
     безоп
    -0.20
    èķº
    -0.20
    ymology
    -0.20
    pers
    -0.19
    ç»Ħç»ĩçĶŁæ´»
    -0.19
    تÙĥÙĪÙĨ
    -0.19
    POSITIVE LOGITS
     negó
    0.21
    æŀķ
    0.20
     allem
    0.20
     grö
    0.20
     (!((
    0.20
    comings
    0.19
     xamarin
    0.19
    .AddField
    0.18
    ++]=
    0.18
    :size
    0.18
    Activations Density 0.000%

    No Known Activations