© 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. 87691
    Prev
    Next
    INDEX
    Explanations

    ordinary things and 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
    143
    -0.11
     disturbance
    -0.08
     Comfort
    -0.08
     kort
    -0.08
     detailed
    -0.08
     elo
    -0.08
     Jah
    -0.08
    iba
    -0.08
     Brewery
    -0.08
    ¶ļ
    -0.08
    POSITIVE LOGITS
     mundane
    0.22
     otherwise
    0.19
     life
    0.19
     proceedings
    0.18
    otherwise
    0.17
     ordinary
    0.16
     Ordinary
    0.15
     boring
    0.15
     everyday
    0.15
     Mondays
    0.14
    Activations Density 0.113%

    No Known Activations