© 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. 87807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cad
    -0.11
     allot
    -0.09
     Cad
    -0.09
    arena
    -0.08
     mug
    -0.07
     Mun
    -0.07
    Cad
    -0.07
     recurs
    -0.07
     MMC
    -0.07
     komt
    -0.07
    POSITIVE LOGITS
     meant
    0.11
     neatly
    0.11
    ((↵
    0.11
    olley
    0.10
     Burl
    0.10
    urr
    0.10
     Natal
    0.10
    tle
    0.10
     Toll
    0.10
     organised
    0.10
    Activations Density 0.000%

    No Known Activations