© 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. 8316
    Prev
    Next
    INDEX
    Explanations

    and I

    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
    âĢ¦.
    -0.09
     THAT
    -0.09
    .......
    -0.09
     if
    -0.09
     there
    -0.08
     when
    -0.08
     {}.
    -0.08
     something
    -0.08
    ..
    -0.08
    âĢ¦âĢ¦
    -0.08
    POSITIVE LOGITS
    ients
    0.13
     others
    0.13
    /or
    0.11
    erson
    0.10
    lek
    0.10
     Were
    0.10
     several
    0.10
     alike
    0.10
    plies
    0.10
     crew
    0.10
    Activations Density 0.080%

    No Known Activations