© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    writing essays

    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
    odka
    -0.23
    /goto
    -0.22
     }}"><
    -0.21
    .GridView
    -0.21
    glyphicon
    -0.20
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.20
    -caret
    -0.20
     Bast
    -0.20
    HasColumnName
    -0.20
    æĻ®åıĬ
    -0.20
    POSITIVE LOGITS
     Writing
    0.29
     Writer
    0.28
     writing
    0.28
     essay
    0.27
    Writing
    0.27
     Writers
    0.26
     essays
    0.25
    essay
    0.25
     paper
    0.24
    Writer
    0.24
    Activations Density 0.135%

    No Known Activations