© 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. 4629
    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
     carrier
    -0.09
     forfe
    -0.09
    ago
    -0.09
     forte
    -0.09
     unas
    -0.09
    GMT
    -0.09
    CTS
    -0.09
     Dart
    -0.08
     comedian
    -0.08
     crowned
    -0.08
    POSITIVE LOGITS
     Trends
    0.10
     antiqu
    0.10
    Offline
    0.10
    emark
    0.09
     trends
    0.09
     Another
    0.09
    eva
    0.09
     concatenated
    0.09
     legality
    0.09
    etest
    0.09
    Activations Density 0.000%

    No Known Activations