© 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. 87839
    Prev
    Next
    INDEX
    Explanations

    license, serial number, comment count

    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
    ç¤
    -0.10
    usa
    -0.10
     mens
    -0.09
     Mull
    -0.09
     stones
    -0.09
     circ
    -0.09
    itas
    -0.09
     Dere
    -0.08
     mort
    -0.08
     usa
    -0.08
    POSITIVE LOGITS
     withhold
    0.10
     Kris
    0.09
     Prot
    0.09
     Barb
    0.09
     heir
    0.09
     caut
    0.09
     desperation
    0.08
     Thames
    0.08
     linked
    0.08
     ware
    0.08
    Activations Density 0.003%

    No Known Activations