© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114583
    Prev
    Next
    INDEX
    Explanations

    universities and institutions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Perf
    -0.09
     Gab
    -0.09
     gab
    -0.09
     Euros
    -0.08
     Jade
    -0.08
     Ravens
    -0.08
     Poetry
    -0.08
     poetry
    -0.08
    vid
    -0.08
     sporting
    -0.07
    POSITIVE LOGITS
     Indiana
    0.13
     contro
    0.13
    Indiana
    0.12
     famously
    0.12
     Voy
    0.12
     Rockefeller
    0.12
     landmark
    0.12
     scientifically
    0.11
     relativ
    0.11
     groundbreaking
    0.11
    Activations Density 0.092%

    No Known Activations