© 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. 30001
    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
     seat
    -0.10
     sab
    -0.09
     merc
    -0.08
     Sab
    -0.08
     downs
    -0.08
     stern
    -0.08
     mid
    -0.08
    Norm
    -0.07
     Seat
    -0.07
     dpi
    -0.07
    POSITIVE LOGITS
    onet
    0.11
    oplay
    0.11
    lashes
    0.11
    fusion
    0.11
    backward
    0.10
     omission
    0.10
     Gir
    0.10
     filtr
    0.10
    /feed
    0.10
     disappoint
    0.10
    Activations Density 0.000%

    No Known Activations