© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112039
    Prev
    Next
    INDEX
    Explanations

    font-family declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    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
     tether
    -0.11
    .colorbar
    -0.11
     rew
    -0.11
    .setAuto
    -0.11
     Verse
    -0.10
     pled
    -0.10
     iterative
    -0.10
    Translations
    -0.10
    :green
    -0.10
     bist
    -0.10
    POSITIVE LOGITS
    .ttf
    0.21
     font
    0.17
     serif
    0.16
     fonts
    0.16
     UIFont
    0.15
     sans
    0.15
    /fonts
    0.14
     Font
    0.14
    .FONT
    0.14
     bold
    0.14
    Activations Density 0.428%

    No Known Activations