© 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. 25078
    Prev
    Next
    INDEX
    Explanations

    Hall or hall followed by word parts

    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
    oles
    -0.12
    ted
    -0.11
    elo
    -0.10
    eous
    -0.09
     Constit
    -0.09
    ELS
    -0.09
    ledge
    -0.08
    yre
    -0.08
    ELY
    -0.08
    lian
    -0.08
    POSITIVE LOGITS
    ways
    0.24
    marks
    0.21
    iday
    0.17
    ows
    0.16
    marked
    0.16
    pike
    0.14
    way
    0.14
    oran
    0.14
    ifax
    0.13
    iards
    0.12
    Activations Density 0.030%

    No Known Activations