© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1226
    Prev
    Next
    INDEX
    Explanations

    therefore, thus, then

    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
    postalcode
    -0.24
    entiful
    -0.20
    麽
    -0.20
    ilogy
    -0.20
    Apellido
    -0.19
    æīĢæīĢ
    -0.19
    大家éĥ½åľ¨
    -0.19
    ilmington
    -0.19
    æŀģåĬĽ
    -0.19
    \db
    -0.19
    POSITIVE LOGITS
     therefore
    0.70
     however
    0.60
    ä¹ŁåĽłæѤ
    0.56
     thus
    0.55
     also
    0.54
    åĽłæѤ
    0.54
     then
    0.51
    however
    0.48
    åĪĻ
    0.46
    åĽłèĢĮ
    0.45
    Activations Density 4.865%

    No Known Activations