© 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. 89805
    Prev
    Next
    INDEX
    Explanations

    earth, soil, mud, clay, sand

    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
     caffeine
    -0.11
     nit
    -0.09
    caffe
    -0.09
     Tender
    -0.09
     popcorn
    -0.09
     Nit
    -0.08
     tink
    -0.08
     dom
    -0.08
     Nev
    -0.08
     caffe
    -0.08
    POSITIVE LOGITS
     mud
    0.62
     Mud
    0.55
     muddy
    0.53
     clay
    0.37
     Clay
    0.32
     dirt
    0.31
     Dirt
    0.29
     soil
    0.27
     swamp
    0.25
     Soil
    0.25
    Activations Density 0.191%

    No Known Activations