© 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. 31629
    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
    éri
    -0.12
     Newman
    -0.09
    adar
    -0.09
    onde
    -0.09
    vor
    -0.09
     draining
    -0.09
    é£
    -0.09
    azio
    -0.09
    ãģ§ãĤĤ
    -0.09
     run
    -0.09
    POSITIVE LOGITS
    s
    0.10
     desn
    0.09
     casual
    0.08
     Toe
    0.08
     sais
    0.08
     Oval
    0.08
     idle
    0.08
    zos
    0.08
    agle
    0.07
    cel
    0.07
    Activations Density 0.000%

    No Known Activations