© 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. 91124
    Prev
    Next
    INDEX
    Explanations

    biocompatible, safe, plausible

    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
     rides
    -0.08
     ride
    -0.08
    wy
    -0.08
    ride
    -0.08
    umph
    -0.08
     Guides
    -0.07
     sway
    -0.07
    hem
    -0.07
     Felix
    -0.07
    Susp
    -0.07
    POSITIVE LOGITS
     materials
    0.16
     ingredients
    0.15
     chemicals
    0.15
    ingredients
    0.12
    materials
    0.12
     Materials
    0.12
    -cert
    0.12
    bic
    0.12
     compliant
    0.11
     renewal
    0.11
    Activations Density 0.006%

    No Known Activations