© 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. 15106
    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
    warnings
    -0.09
     hail
    -0.09
     ge
    -0.08
     strat
    -0.08
    omal
    -0.08
     authentic
    -0.08
     regenerated
    -0.08
     unsub
    -0.08
    sons
    -0.08
     fragment
    -0.08
    POSITIVE LOGITS
     Rae
    0.11
     crossed
    0.10
     Midi
    0.10
    fx
    0.10
    arna
    0.10
    ideshow
    0.09
     ringing
    0.09
     Nich
    0.09
    hipster
    0.09
     Rouge
    0.09
    Activations Density 0.000%

    No Known Activations