© 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. 111367
    Prev
    Next
    INDEX
    Explanations

    link below

    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
     tro
    -0.11
     primaries
    -0.09
     Ree
    -0.09
     pros
    -0.09
     mines
    -0.09
    ider
    -0.08
     (...
    -0.08
     boiler
    -0.08
     dispon
    -0.08
     retr
    -0.08
    POSITIVE LOGITS
    Merc
    0.10
     Til
    0.10
     Batt
    0.10
    lasting
    0.09
     Fox
    0.09
    matter
    0.09
    graf
    0.09
    oped
    0.09
     ages
    0.09
    fos
    0.09
    Activations Density 0.001%

    No Known Activations