© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48458
    Prev
    Next
    INDEX
    Explanations

    reporting speech or 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
    kel
    -0.10
    law
    -0.10
     Replica
    -0.10
     Paran
    -0.10
     Holt
    -0.09
     confess
    -0.09
     dialect
    -0.09
     Dia
    -0.09
     stag
    -0.09
    adero
    -0.09
    POSITIVE LOGITS
     smile
    0.10
     continue
    0.10
     continuation
    0.10
     infinitely
    0.09
     smiles
    0.09
     smiling
    0.09
     continuing
    0.09
    inas
    0.09
     she
    0.09
     eff
    0.09
    Activations Density 0.007%

    No Known Activations