© 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. 14494
    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
     PROT
    -0.11
     Tomb
    -0.11
     requ
    -0.10
    iser
    -0.10
     Meadow
    -0.10
     mono
    -0.10
    ks
    -0.10
     gravid
    -0.10
    /ay
    -0.10
    apo
    -0.10
    POSITIVE LOGITS
     Fritz
    0.08
     cosy
    0.08
     credible
    0.08
     Huckabee
    0.08
     Huck
    0.08
    our
    0.08
    baz
    0.07
     Prov
    0.07
    .hu
    0.07
     listening
    0.07
    Activations Density 0.000%

    No Known Activations