© 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. 115007
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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
    ettle
    -0.10
     Integrity
    -0.10
     Lac
    -0.09
     conserve
    -0.09
    ido
    -0.08
     Rossi
    -0.08
     Flat
    -0.08
    itti
    -0.08
     WHETHER
    -0.08
    bid
    -0.08
    POSITIVE LOGITS
     sang
    0.10
    vido
    0.09
    dk
    0.09
     Daly
    0.09
     misunder
    0.09
     Hear
    0.09
     necess
    0.09
     mig
    0.09
    redis
    0.09
     reconstruct
    0.08
    Activations Density 0.028%

    No Known Activations