© 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. 25624
    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
    ippet
    -0.09
     glitch
    -0.08
     pretend
    -0.08
    utex
    -0.08
    ADA
    -0.08
     reluct
    -0.08
     pretending
    -0.08
     confession
    -0.08
     failing
    -0.08
     fend
    -0.08
    POSITIVE LOGITS
     dominates
    0.09
     dominated
    0.09
    iks
    0.09
    isti
    0.09
     DOS
    0.09
    uv
    0.09
     Ruf
    0.09
    laus
    0.09
     dominate
    0.09
     Nes
    0.09
    Activations Density 0.000%

    No Known Activations