© 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. 33182
    Prev
    Next
    INDEX
    Explanations

    Redistribution and license terms

    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
     thats
    -0.11
    -0.10
    mans
    -0.10
    -0.09
     whats
    -0.09
     allot
    -0.09
     Aws
    -0.09
     af
    -0.09
    ´s
    -0.09
     geg
    -0.09
    POSITIVE LOGITS
     understandably
    0.10
     corrobor
    0.10
     --↵↵
    0.10
    --↵
    0.09
     Tent
    0.09
     Arbor
    0.09
     EITHER
    0.09
    /etc
    0.09
    --↵↵
    0.09
     rede
    0.09
    Activations Density 0.139%

    No Known Activations