© 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. 50850
    Prev
    Next
    INDEX
    Explanations

    message 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
     unpleasant
    -0.12
     dubious
    -0.12
     eventually
    -0.12
     Eventually
    -0.12
     später
    -0.11
    dac
    -0.11
     blah
    -0.11
     Later
    -0.11
    later
    -0.11
     finer
    -0.11
    POSITIVE LOGITS
     still
    0.12
     simultaneously
    0.12
     now
    0.11
     STILL
    0.11
     again
    0.10
     simult
    0.10
     Still
    0.09
     Again
    0.09
     meanwhile
    0.09
     Continuing
    0.09
    Activations Density 0.036%

    No Known Activations