© 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. 17176
    Prev
    Next
    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     gradu
    -0.09
    ós
    -0.09
     unpredict
    -0.09
     unlike
    -0.09
     herein
    -0.09
     unfortunately
    -0.09
     hum
    -0.09
     Fond
    -0.08
     Prop
    -0.08
    ours
    -0.08
    POSITIVE LOGITS
     Instead
    0.16
     instead
    0.15
    Instead
    0.14
    instead
    0.13
     Nay
    0.11
    /dis
    0.10
     bastard
    0.10
    only
    0.10
     Rather
    0.10
    shade
    0.10
    Activations Density 0.003%

    No Known Activations