© 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. 15464
    Prev
    Next
    INDEX
    Explanations

    significant breakthroughs and impact

    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
    atu
    -0.11
    Lov
    -0.10
     intimidating
    -0.10
    icks
    -0.10
    oves
    -0.09
     Invocation
    -0.09
     somehow
    -0.09
    nel
    -0.09
     Herman
    -0.09
    _sd
    -0.09
    POSITIVE LOGITS
     revolution
    0.22
     revolutionary
    0.19
     breakthrough
    0.17
     fame
    0.17
     groundbreaking
    0.17
     Fame
    0.16
     Revolution
    0.16
     unprecedented
    0.15
     potentially
    0.15
     Nobel
    0.15
    Activations Density 0.198%

    No Known Activations