© 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. 111488
    Prev
    Next
    INDEX
    Explanations

    large quantities or size

    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
    Small
    -0.11
     Small
    -0.11
    small
    -0.11
     vast
    -0.10
     small
    -0.09
     Eyes
    -0.09
    _small
    -0.09
     SMALL
    -0.09
    thouse
    -0.09
    835
    -0.08
    POSITIVE LOGITS
     lump
    0.15
     juicy
    0.12
     bunch
    0.12
     bundle
    0.11
     fucking
    0.10
    -sized
    0.10
     handful
    0.10
     stack
    0.10
     bru
    0.10
     Oro
    0.10
    Activations Density 0.016%

    No Known Activations