© 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. 48573
    Prev
    Next
    INDEX
    Explanations

    having been + past participle

    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
     being
    -0.19
    Being
    -0.17
     Being
    -0.16
    being
    -0.16
    -being
    -0.13
    undler
    -0.12
    -mouth
    -0.12
    è¢
    -0.12
     бÑĭÑĤÑĮ
    -0.11
     currently
    -0.11
    POSITIVE LOGITS
    /is
    0.21
     able
    0.17
     instrumental
    0.12
     unable
    0.11
     born
    0.10
     previously
    0.10
    /am
    0.10
     recently
    0.10
     unsuccessful
    0.09
     successful
    0.09
    Activations Density 0.179%

    No Known Activations