© 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. 50895
    Prev
    Next
    INDEX
    Explanations

    words after 'the'

    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
     aver
    -0.09
    ib
    -0.09
     Stark
    -0.09
     sinon
    -0.09
    unan
    -0.09
    ollah
    -0.09
     constraints
    -0.09
     Reno
    -0.09
     restrictions
    -0.09
     exh
    -0.09
    POSITIVE LOGITS
     ego
    0.11
     wand
    0.11
     vanity
    0.11
     hair
    0.10
    ingles
    0.09
     Beard
    0.09
     beard
    0.09
     forcibly
    0.09
     FCC
    0.09
    quiring
    0.09
    Activations Density 0.003%

    No Known Activations