© 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. 89639
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation

    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
     caution
    -0.12
     understandably
    -0.12
     unfortunate
    -0.11
    ufe
    -0.11
     Pearce
    -0.11
     certainly
    -0.10
    elas
    -0.10
     firstly
    -0.10
     otherwise
    -0.10
     hopefully
    -0.10
    POSITIVE LOGITS
     actually
    0.13
     somehow
    0.12
    actually
    0.10
     kicker
    0.09
     THEN
    0.09
     subsequent
    0.09
    è
    0.09
    flo
    0.09
     actively
    0.09
    ç«
    0.09
    Activations Density 0.094%

    No Known Activations