© 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. 50912
    Prev
    Next
    INDEX
    Explanations

    activities

    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
     pimp
    -0.09
     summers
    -0.09
     glimpse
    -0.09
    365
    -0.09
     feud
    -0.09
    adero
    -0.09
     glance
    -0.09
     Props
    -0.09
     cigar
    -0.08
     eye
    -0.08
    POSITIVE LOGITS
     activities
    0.18
     Activities
    0.14
     stren
    0.14
     walking
    0.13
     activ
    0.13
    Activities
    0.12
     activity
    0.12
    activities
    0.12
     dancing
    0.12
     actividades
    0.11
    Activations Density 0.125%

    No Known Activations