© 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. 34031
    Prev
    Next
    INDEX
    Explanations

    of others

    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
     Nos
    -0.12
    or
    -0.11
    ose
    -0.11
    dn
    -0.11
     noses
    -0.11
    ats
    -0.11
    them
    -0.10
    uctor
    -0.10
    oner
    -0.10
    ellers
    -0.10
    POSITIVE LOGITS
     others
    0.15
    others
    0.11
     individuals
    0.10
     millions
    0.09
     MANY
    0.08
     mankind
    0.08
     rss
    0.08
    itta
    0.08
     fle
    0.07
     everyone
    0.07
    Activations Density 0.359%

    No Known Activations