© 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. 96
    Prev
    Next
    INDEX
    Explanations

    code styling

    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
    çī¢è®°ä½¿åij½
    -0.23
    è´¨
    -0.22
    Serviço
    -0.21
     yal
    -0.21
    	extern
    -0.21
     misunder
    -0.21
    @AllArgsConstructor
    -0.20
    ãİĿ
    -0.20
    æį¢æĿ¥
    -0.20
     matchups
    -0.19
    POSITIVE LOGITS
     withStyles
    0.27
    0.23
     (![
    0.21
    (SYS
    0.21
     makeStyles
    0.20
    ỵ
    0.20
    ]={↵
    0.20
    âŀ¥
    0.20
    AllowAnonymous
    0.20
    nek
    0.19
    Activations Density 1.085%

    No Known Activations