© 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. 15925
    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
    mand
    -0.08
     swollen
    -0.07
     mandate
    -0.07
    agn
    -0.07
    oval
    -0.07
    usch
    -0.07
    uling
    -0.07
    ARB
    -0.06
     whitelist
    -0.06
     amended
    -0.06
    POSITIVE LOGITS
     tav
    0.11
    logan
    0.11
     reassuring
    0.11
     laut
    0.11
     enh
    0.11
    assi
    0.11
     erot
    0.10
     coarse
    0.10
    ynes
    0.10
     Harris
    0.10
    Activations Density 0.000%

    No Known Activations