© 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. 15595
    Prev
    Next
    INDEX
    Explanations

    formatting and content quality

    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
     stren
    -0.09
    Soup
    -0.09
     proceedings
    -0.09
    rez
    -0.09
     demolished
    -0.09
    agus
    -0.08
     guts
    -0.08
    illos
    -0.08
     programm
    -0.08
     speeches
    -0.08
    POSITIVE LOGITS
     punctuation
    0.28
     formatting
    0.28
     grammar
    0.26
     spelling
    0.26
     illustrations
    0.24
     gramm
    0.24
     Formatting
    0.23
     vocabulary
    0.21
     pictures
    0.21
     graphics
    0.20
    Activations Density 0.845%

    No Known Activations