© 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. 47479
    Prev
    Next
    INDEX
    Explanations

    wildlife, habitat, species, biodiversity

    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
    Ãľ
    -0.10
    bomb
    -0.09
     pawn
    -0.09
     possession
    -0.09
    ifax
    -0.09
     rico
    -0.09
     Dante
    -0.09
    ubits
    -0.09
     conqu
    -0.09
     Modern
    -0.09
    POSITIVE LOGITS
     wildlife
    0.34
     conservation
    0.32
     biodiversity
    0.31
     endangered
    0.30
     habitat
    0.30
     Conservation
    0.30
     Wildlife
    0.29
     habitats
    0.29
     species
    0.29
     Species
    0.25
    Activations Density 0.948%

    No Known Activations