© 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. 30397
    Prev
    Next
    INDEX
    Explanations

    consequently, resulting, whenever

    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
     Afterwards
    -0.13
     Suddenly
    -0.13
     suddenly
    -0.12
     afterwards
    -0.12
    Suddenly
    -0.12
     momentarily
    -0.11
     eventually
    -0.11
     THEN
    -0.11
    Then
    -0.11
     Wonder
    -0.11
    POSITIVE LOGITS
     consequently
    0.16
     Consequently
    0.16
     consequence
    0.14
     consequ
    0.13
     resulting
    0.13
     frequently
    0.13
     whenever
    0.12
     Whenever
    0.11
     rarely
    0.11
     routinely
    0.11
    Activations Density 0.051%

    No Known Activations