© 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. 50861
    Prev
    Next
    INDEX
    Explanations

    Mrs. followed by a name

    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
     wides
    -0.10
     perman
    -0.09
     wide
    -0.09
     dis
    -0.09
    kins
    -0.09
    -transparent
    -0.09
    lasting
    -0.09
    rosse
    -0.09
     Porno
    -0.09
    resse
    -0.09
    POSITIVE LOGITS
     Thatcher
    0.11
     Whats
    0.10
    esh
    0.09
    (.)
    0.09
    achten
    0.08
    .mouse
    0.08
     chatter
    0.08
    utar
    0.08
     brow
    0.08
    uffle
    0.08
    Activations Density 0.019%

    No Known Activations