© 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. 49865
    Prev
    Next
    INDEX
    Explanations

    sirens, drowning, lurers, rescue

    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
    (Web
    -0.09
     ado
    -0.09
     chrono
    -0.09
     CSA
    -0.09
     nic
    -0.09
     Pence
    -0.09
     Tob
    -0.09
    chap
    -0.09
     Afr
    -0.09
     Fle
    -0.08
    POSITIVE LOGITS
     sire
    0.16
     Ariel
    0.13
     drowned
    0.12
    iren
    0.11
     drowning
    0.11
     Lore
    0.11
     mainland
    0.10
     Rescue
    0.10
     Mariners
    0.10
     lure
    0.09
    Activations Density 0.042%

    No Known Activations