© 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. 523
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
    berra
    -0.32
    âļĹ
    -0.31
    ðŁĵIJ
    -0.30
    ./(
    -0.29
    âĦī
    -0.27
    :<?
    -0.25
     Ä°l
    -0.24
    onsense
    -0.23
    aturdays
    -0.23
    Türkiye
    -0.23
    POSITIVE LOGITS
     isn
    0.32
     aren
    0.30
     hasn
    0.29
     just
    0.28
     ain
    0.28
    're
    0.27
    åıĭæĥħéĵ¾æİ¥
    0.27
     wasn
    0.27
    ’re
    0.26
     doesn
    0.26
    Activations Density 3.941%

    No Known Activations