© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50755
    Prev
    Next
    INDEX
    Explanations

    frequency and time

    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
    Negative Logits
     unless
    -0.11
     whichever
    -0.10
    unless
    -0.10
     Sang
    -0.09
     barring
    -0.09
     ti
    -0.09
    except
    -0.09
    TI
    -0.09
     bri
    -0.09
     mast
    -0.09
    POSITIVE LOGITS
     yearly
    0.16
     annually
    0.15
     nowadays
    0.15
     daily
    0.13
     hoping
    0.13
    -many
    0.13
     either
    0.13
     today
    0.12
     worldwide
    0.11
     simultaneously
    0.11
    Activations Density 0.568%

    No Known Activations