© 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. 117486
    Prev
    Next
    INDEX
    Explanations

    things that are funny

    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
     Enjoy
    -0.10
    Enjoy
    -0.09
    sume
    -0.09
     enjoy
    -0.09
    xo
    -0.09
     enjoyed
    -0.08
    aq
    -0.08
    ois
    -0.08
     enjoying
    -0.08
    igm
    -0.08
    POSITIVE LOGITS
    -shaped
    0.14
    -looking
    0.13
     shaped
    0.13
    -money
    0.13
     thing
    0.12
     little
    0.12
    /we
    0.11
     enough
    0.10
    ï¼Īç¬ij
    0.10
    headed
    0.10
    Activations Density 0.009%

    No Known Activations