© 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. 92585
    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
    chos
    -0.11
    nest
    -0.11
    inte
    -0.11
    iq
    -0.11
    eli
    -0.11
     originating
    -0.10
     clos
    -0.10
     Flour
    -0.10
     stud
    -0.10
     Kia
    -0.10
    POSITIVE LOGITS
     scratched
    0.09
    stamp
    0.09
     rainbow
    0.08
     fant
    0.08
     Carn
    0.08
     cr
    0.08
     deadline
    0.08
    оваÑĢ
    0.08
     irreversible
    0.08
     Scratch
    0.08
    Activations Density 0.000%

    No Known Activations