© 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. 2277
    Prev
    Next
    INDEX
    Explanations

    order

    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
    ãİı
    -0.25
    讵
    -0.24
    ä¸ĸ纪
    -0.22
    娣
    -0.21
    ðŁ¤Ĺ
    -0.20
    /AFP
    -0.19
     Advent
    -0.19
    éļĪ
    -0.19
    ä¸įåĩºæĿ¥
    -0.18
    æľĢåıĹ
    -0.18
    POSITIVE LOGITS
     rencont
    0.27
    ltra
    0.26
     inkl
    0.24
    ADIO
    0.22
    tility
    0.21
     stringWith
    0.20
    irlines
    0.20
    minent
    0.19
     ESV
    0.19
    osate
    0.19
    Activations Density 0.269%

    No Known Activations