© 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. 28181
    Prev
    Next
    INDEX
    Explanations

    crystal and crystallography

    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
    -0.09
     paint
    -0.09
     Painting
    -0.09
    poi
    -0.09
     pneum
    -0.08
    paint
    -0.08
     coin
    -0.08
     Lv
    -0.08
     Cole
    -0.08
     cork
    -0.08
    POSITIVE LOGITS
     crystal
    0.44
     Crystal
    0.39
     crystals
    0.38
    Crystal
    0.37
     crystall
    0.36
     cryst
    0.32
     crist
    0.24
    CRY
    0.22
    -cr
    0.19
     lattice
    0.19
    Activations Density 0.525%

    No Known Activations