© 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. 117588
    Prev
    Next
    INDEX
    Explanations

    across, throughout, around

    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
     Dro
    -0.11
     dro
    -0.10
     Lub
    -0.10
     dusty
    -0.09
    flo
    -0.09
     backstage
    -0.08
    ona
    -0.08
    agate
    -0.08
     Bras
    -0.08
     cong
    -0.08
    POSITIVE LOGITS
     fingertips
    0.14
     fingert
    0.12
     walls
    0.12
     tip
    0.11
     entire
    0.11
     umbrella
    0.10
     Entire
    0.09
     tips
    0.09
     intuition
    0.09
    borg
    0.09
    Activations Density 0.163%

    No Known Activations