© 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. 117229
    Prev
    Next
    INDEX
    Explanations

    common areas in buildings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Jacqu
    -0.10
     subroutine
    -0.10
     Eis
    -0.10
     marks
    -0.10
     Jude
    -0.10
     Ja
    -0.09
     Toilet
    -0.09
    cea
    -0.09
    /framework
    -0.09
     Ged
    -0.09
    POSITIVE LOGITS
     lobby
    0.25
     downstairs
    0.24
     lounge
    0.24
     communal
    0.23
     Lounge
    0.20
     commons
    0.19
     loung
    0.19
    lobby
    0.17
     public
    0.16
     living
    0.16
    Activations Density 0.206%

    No Known Activations