© 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. 46381
    Prev
    Next
    INDEX
    Explanations

    mathematical division questions

    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
    lesh
    -0.08
     Mash
    -0.07
     Lands
    -0.07
    oppable
    -0.07
    assed
    -0.07
     Sac
    -0.07
     Photon
    -0.07
    awe
    -0.07
    ajo
    -0.07
     lands
    -0.07
    POSITIVE LOGITS
     counterparts
    0.11
     examples
    0.10
     Kata
    0.10
     wurden
    0.10
     entail
    0.10
    atz
    0.10
     weren
    0.10
     prizes
    0.10
     пÑĢи
    0.10
    ony
    0.10
    Activations Density 0.007%

    No Known Activations