© 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. 87745
    Prev
    Next
    INDEX
    Explanations

    fork me on GitHub

    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
     ours
    -0.23
     ourselves
    -0.19
     Personally
    -0.12
    Personally
    -0.12
     hers
    -0.11
     McM
    -0.11
    ours
    -0.10
     us
    -0.10
     mys
    -0.10
    (()=>
    -0.09
    POSITIVE LOGITS
     gim
    0.10
     :'
    0.09
    _exc
    0.09
    åħ¬
    0.09
     rav
    0.09
     desper
    0.09
    ativ
    0.09
    isse
    0.09
     Shoot
    0.09
    Hu
    0.08
    Activations Density 0.116%

    No Known Activations