© 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. 47946
    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
    agnostic
    -0.10
    handled
    -0.10
     Ord
    -0.09
     avis
    -0.09
     staging
    -0.09
    char
    -0.09
    inc
    -0.08
    fel
    -0.08
     uncomfort
    -0.08
     Cunning
    -0.08
    POSITIVE LOGITS
    pire
    0.12
     whirl
    0.10
    bia
    0.10
     whisk
    0.10
     æĸ
    0.10
     intermediary
    0.10
    Archive
    0.09
     intermediate
    0.09
    pend
    0.09
     Smy
    0.09
    Activations Density 0.000%

    No Known Activations