© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     agon
    -0.08
     Rudd
    -0.08
     pledges
    -0.08
     ju
    -0.08
     lor
    -0.07
     Watkins
    -0.07
     dwell
    -0.07
     residuals
    -0.07
    lä
    -0.07
     [&
    -0.07
    POSITIVE LOGITS
     lump
    0.13
     HIT
    0.13
     enough
    0.12
     erection
    0.12
    copy
    0.11
    ens
    0.11
     dick
    0.11
    inges
    0.10
    azzi
    0.10
    enis
    0.10
    Activations Density 0.000%

    No Known Activations