© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    technical or descriptive terms

    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
     scrut
    -0.23
    åĪļ
    -0.21
    æĺĢ
    -0.21
    1
    -0.20
     slogans
    -0.20
     gays
    -0.20
     dhe
    -0.19
    4
    -0.19
    5
    -0.19
     jean
    -0.19
    POSITIVE LOGITS
    .BorderFactory
    0.32
    ä¸Ģèĩ´å¥½è¯Ħ
    0.28
    趿
    0.27
    .BackgroundImage
    0.26
    èĵĬ
    0.25
    èĻĵ
    0.25
    .ImageIcon
    0.24
    åĭį
    0.24
    éĶ
    0.24
    .firebaseio
    0.24
    Activations Density 0.081%

    No Known Activations