© 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. 4984
    Prev
    Next
    INDEX
    Explanations

    continuation

    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
     beginning
    -0.11
    æĸĻ
    -0.11
    (start
    -0.11
    -start
    -0.11
     staying
    -0.11
     beginnings
    -0.11
     Ald
    -0.11
    <?,
    -0.11
     conce
    -0.11
     keeping
    -0.11
    POSITIVE LOGITS
     unab
    0.15
     unchecked
    0.12
     uninterrupted
    0.11
     intermitt
    0.09
     spor
    0.08
     inex
    0.08
     until
    0.08
    ermann
    0.08
     unfold
    0.08
    ella
    0.08
    Activations Density 0.059%

    No Known Activations