© 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. 33570
    Prev
    Next
    INDEX
    Explanations

    coal mining and industry

    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
     Tiny
    -0.09
     circulation
    -0.09
    uur
    -0.08
    emat
    -0.08
    wald
    -0.08
     circuits
    -0.08
    etur
    -0.08
     Oliv
    -0.08
    ahi
    -0.08
     scoped
    -0.08
    POSITIVE LOGITS
     coal
    0.24
    coal
    0.24
     Seam
    0.20
     Coal
    0.19
    Coal
    0.19
    itions
    0.18
     seam
    0.17
     miner
    0.16
    -fired
    0.16
    mine
    0.16
    Activations Density 0.032%

    No Known Activations