© 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. 2453
    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
     holland
    -0.21
    /ext
    -0.21
     coordin
    -0.20
    .');
    -0.20
     __________________↵↵
    -0.19
    ceive
    -0.19
     incontro
    -0.19
    éģ¿ãģij
    -0.19
    ARSE
    -0.19
     blouse
    -0.18
    POSITIVE LOGITS
     Deze
    0.23
     Natürlich
    0.22
    NIC
    0.21
    鬣
    0.19
     Peb
    0.19
     AuÃŁerdem
    0.19
    éħ¡
    0.18
    gne
    0.18
     //!<
    0.18
    çĽijçĿ£ç®¡çIJĨ
    0.18
    Activations Density 0.000%

    No Known Activations