© 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. 1800
    Prev
    Next
    INDEX
    Explanations

    by by by

    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
    æľĭåıĭ们对
    -0.24
     bergen
    -0.21
    arin
    -0.20
    #echo
    -0.20
     TArray
    -0.19
    isclosed
    -0.19
    对åħ¬åı¸
    -0.19
    çħĬ
    -0.18
     Marketable
    -0.18
    é²ł
    -0.18
    POSITIVE LOGITS
     by
    0.79
     oleh
    0.64
    çĶ±
    0.62
    by
    0.58
    å¹´çĶ±
    0.54
    _by
    0.50
    çĶ±ä¸ŃåĽ½
    0.50
    åĿĩçĶ±
    0.47
    æĿ¥èĩª
    0.47
    edBy
    0.47
    Activations Density 3.302%

    No Known Activations