© 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. 29695
    Prev
    Next
    INDEX
    Explanations

    renovating places

    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
     flap
    -0.11
     orally
    -0.11
     dispatched
    -0.10
    ope
    -0.10
     Seg
    -0.10
    folk
    -0.10
    Via
    -0.10
    peech
    -0.10
     segmented
    -0.10
    uhe
    -0.10
    POSITIVE LOGITS
     rooms
    0.17
     classrooms
    0.16
     everything
    0.13
     bathrooms
    0.13
     surroundings
    0.13
     offices
    0.12
     workplaces
    0.12
    everything
    0.12
     Rooms
    0.12
     bedrooms
    0.11
    Activations Density 0.191%

    No Known Activations