© 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. 90469
    Prev
    Next
    INDEX
    Explanations

    pumpkin spices and squash

    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
     coin
    -0.10
     dolphin
    -0.10
     Leopard
    -0.09
     Marina
    -0.09
     leopard
    -0.09
     basil
    -0.09
     pearls
    -0.09
    abajo
    -0.09
     Laboratory
    -0.09
     submar
    -0.09
    POSITIVE LOGITS
     pumpkin
    0.25
     Pumpkin
    0.22
     carving
    0.15
     Pump
    0.13
     pump
    0.13
     squash
    0.12
     Halloween
    0.11
     Hait
    0.11
     Orchard
    0.10
     orange
    0.10
    Activations Density 0.349%

    No Known Activations