© 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. 111509
    Prev
    Next
    INDEX
    Explanations

    outcomes or conclusions

    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
    ters
    -0.11
     extensively
    -0.10
     exaggerated
    -0.09
     cork
    -0.09
     Cork
    -0.09
     vert
    -0.08
    vre
    -0.08
    iones
    -0.08
     Vert
    -0.08
     Poly
    -0.08
    POSITIVE LOGITS
     via
    0.12
    nit
    0.11
     Via
    0.10
     artificially
    0.10
     supervised
    0.10
     Westbrook
    0.09
     Bedrooms
    0.09
    itt
    0.09
     surrogate
    0.09
     dedic
    0.09
    Activations Density 0.042%

    No Known Activations