© 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. 29475
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vir
    -0.10
    bia
    -0.08
     Replies
    -0.08
     replies
    -0.08
     Mush
    -0.08
     poster
    -0.08
     Multimedia
    -0.08
     Recap
    -0.07
    reply
    -0.07
    578
    -0.07
    POSITIVE LOGITS
     precisely
    0.13
     Exactly
    0.13
     exactly
    0.13
     LOL
    0.12
    Exactly
    0.12
     naw
    0.12
     Citation
    0.12
    citation
    0.11
     amen
    0.11
    Yep
    0.11
    Activations Density 0.078%

    No Known Activations