© 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. 90874
    Prev
    Next
    INDEX
    Explanations

    nasal cavities or conditions

    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
     Tib
    -0.09
     bolt
    -0.09
     utter
    -0.09
     chant
    -0.09
     bolts
    -0.09
    Ïī
    -0.09
     Ling
    -0.08
    Verb
    -0.08
     ler
    -0.08
     churn
    -0.08
    POSITIVE LOGITS
     nasal
    0.46
     nose
    0.41
     nostr
    0.40
     Nose
    0.39
     noses
    0.37
     Nas
    0.37
     sniff
    0.34
    nas
    0.29
     nas
    0.27
     rh
    0.23
    Activations Density 0.337%

    No Known Activations