© 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. 117448
    Prev
    Next
    INDEX
    Explanations

    cosmic, cerebral, terrestrial

    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
    house
    -0.11
     Giles
    -0.09
     praying
    -0.09
    iert
    -0.08
    OMET
    -0.08
     widest
    -0.08
    's
    -0.08
    né
    -0.08
     Cunning
    -0.08
     laps
    -0.08
    POSITIVE LOGITS
     Bodies
    0.09
    /local
    0.09
    /o
    0.09
     bureaucracy
    0.09
     Hund
    0.09
     Lew
    0.09
    /material
    0.09
     bureauc
    0.09
     barg
    0.09
    /internal
    0.09
    Activations Density 0.055%

    No Known Activations