© 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. 92352
    Prev
    Next
    INDEX
    Explanations

    bedroom counts

    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
     upstairs
    -0.28
     downstairs
    -0.25
     basement
    -0.23
     Basement
    -0.19
     stairs
    -0.18
    stairs
    -0.17
     cellar
    -0.16
     attic
    -0.16
     stair
    -0.16
     mansion
    -0.15
    POSITIVE LOGITS
    BAL
    0.11
     panoramic
    0.11
    ette
    0.11
     Living
    0.11
     living
    0.10
     Bal
    0.10
     minib
    0.09
    iba
    0.09
     BAL
    0.09
     balcony
    0.09
    Activations Density 0.234%

    No Known Activations