© 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. 16192
    Prev
    Next
    INDEX
    Explanations

    gems and crystals

    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
     sausage
    -0.12
     padd
    -0.11
    PROTO
    -0.11
     printable
    -0.11
     Genius
    -0.11
     kinky
    -0.11
     wraps
    -0.11
     Kawasaki
    -0.10
     Pose
    -0.10
     outdoors
    -0.10
    POSITIVE LOGITS
     crystal
    0.23
     crystals
    0.20
     Crystal
    0.18
     gem
    0.18
    Crystal
    0.16
     gems
    0.16
     glass
    0.16
     transparency
    0.15
     Transparency
    0.14
     Glass
    0.14
    Activations Density 0.096%

    No Known Activations