© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
     @$_
    -0.22
    ä¸ĢåįĬ
    -0.20
    Bas
    -0.20
     propTypes
    -0.19
    .CompareTag
    -0.19
    ä¾ī
    -0.19
    æŀģ大çļĦ
    -0.18
     Falling
    -0.18
    åľĪåŃIJ
    -0.18
    oud
    -0.18
    POSITIVE LOGITS
    erca
    0.24
    bove
    0.23
    layui
    0.23
    olie
    0.22
    :'.$
    0.21
    ç£Ķ
    0.20
    .hasMore
    0.20
    :'',
    0.20
    ãģªãģıãģªãģ£ãģ¦
    0.20
    .Complete
    0.19
    Activations Density 0.073%

    No Known Activations