© 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. 14109
    Prev
    Next
    INDEX
    Explanations

    only the rest

    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
    SHARE
    -0.10
    Merc
    -0.09
    itel
    -0.09
     err
    -0.09
    bert
    -0.09
    lem
    -0.09
    eni
    -0.09
    -ne
    -0.09
    ilit
    -0.08
     hust
    -0.08
    POSITIVE LOGITS
     everything
    0.36
     Everything
    0.31
    everything
    0.31
    Everything
    0.29
     rest
    0.27
     remainder
    0.22
     anything
    0.22
     Anything
    0.21
     otherwise
    0.21
    anything
    0.20
    Activations Density 0.443%

    No Known Activations