© 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. 32402
    Prev
    Next
    INDEX
    Explanations

    rice and grain types

    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
     juices
    -0.10
     legion
    -0.10
     Bass
    -0.09
    ROTO
    -0.09
     juice
    -0.09
     cider
    -0.09
     Trout
    -0.09
     Juice
    -0.09
     Holl
    -0.09
     celery
    -0.09
    POSITIVE LOGITS
     Rice
    0.35
     rice
    0.34
    rice
    0.25
     grains
    0.22
     grain
    0.19
    ç±³
    0.16
     padd
    0.16
     Grain
    0.15
     gran
    0.13
     cereal
    0.13
    Activations Density 0.178%

    No Known Activations