© 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. 297
    Prev
    Next
    INDEX
    Explanations

    or

    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
    /or
    -0.26
    -
    -0.25
    d
    -0.24
    åį´ä¸į
    -0.23
    ä¹Łæĺ¯
    -0.23
     and
    -0.23
    à¸Ļ
    -0.23
     then
    -0.22
    inputEmail
    -0.22
    0
    -0.21
    POSITIVE LOGITS
    phans
    0.58
    ifice
    0.56
    naments
    0.47
    ients
    0.45
    acles
    0.45
    ignal
    0.45
    acular
    0.41
    thon
    0.38
     else
    0.37
    lando
    0.37
    Activations Density 0.830%

    No Known Activations