© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15895
    Prev
    Next
    INDEX
    Explanations

    newest messages or posts

    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
    uci
    -0.10
     resc
    -0.10
    ucken
    -0.09
     Fellow
    -0.09
    ulp
    -0.09
    ieux
    -0.09
     Hover
    -0.09
    ibt
    -0.09
    849
    -0.09
     beds
    -0.09
    POSITIVE LOGITS
     newest
    0.11
     unread
    0.11
     overnight
    0.10
     authored
    0.10
    metro
    0.10
     TM
    0.09
     Barcl
    0.09
     Mall
    0.09
     Mast
    0.09
     hus
    0.08
    Activations Density 0.040%

    No Known Activations