© 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. 4579
    Prev
    Next
    INDEX
    Explanations

    observing things noticed

    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
     Nic
    -0.12
    ech
    -0.11
     forn
    -0.10
    iliary
    -0.10
    itudes
    -0.10
    ace
    -0.10
    rip
    -0.10
    erton
    -0.10
    uby
    -0.10
    uli
    -0.10
    POSITIVE LOGITS
    ably
    0.17
     discrepancies
    0.11
     changes
    0.11
     similarities
    0.10
     differences
    0.10
     trends
    0.10
     inconsistencies
    0.10
     slight
    0.09
     missing
    0.09
     signs
    0.09
    Activations Density 0.021%

    No Known Activations