© 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. 919
    Prev
    Next
    INDEX
    Explanations

    will

    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
     Rencontre
    -0.24
     neighb
    -0.23
     DISCLAIMER
    -0.22
     would
    -0.22
     SolidColorBrush
    -0.21
     africa
    -0.21
     misd
    -0.21
     siti
    -0.20
     explos
    -0.20
     brazil
    -0.20
    POSITIVE LOGITS
    ombat
    0.37
    iams
    0.35
     soon
    0.31
    agged
    0.30
    ngth
    0.29
     likely
    0.29
    ogui
    0.28
    engeance
    0.28
     be
    0.27
    "';
    0.27
    Activations Density 0.924%

    No Known Activations