© 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. 51019
    Prev
    Next
    INDEX
    Explanations

    receive benefits and compensation

    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
     Ernest
    -0.11
     trainable
    -0.10
    allas
    -0.10
     erm
    -0.09
     passion
    -0.09
     Labs
    -0.09
     Fon
    -0.09
     Fut
    -0.09
     labs
    -0.08
     Colony
    -0.08
    POSITIVE LOGITS
     equal
    0.11
     Alert
    0.11
    0.11
     prompt
    0.10
     breaks
    0.10
     alert
    0.10
     Equal
    0.10
     alerts
    0.09
     Discounts
    0.09
     colder
    0.09
    Activations Density 0.005%

    No Known Activations