© 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. 29766
    Prev
    Next
    INDEX
    Explanations

    chemicalchemistryprocessingreactions

    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
    antly
    -0.11
    fulness
    -0.10
     Aval
    -0.10
    nak
    -0.10
    æĪ·
    -0.09
     PARTICULAR
    -0.09
     Tiny
    -0.09
    åĬ¨çĶŁæĪIJ
    -0.09
    /email
    -0.09
    ÃŃstica
    -0.09
    POSITIVE LOGITS
    isor
    0.12
    tracts
    0.11
     reactions
    0.10
     Composition
    0.10
    istry
    0.10
     Reaction
    0.10
     composition
    0.10
     chem
    0.10
     bonded
    0.09
     Chemistry
    0.09
    Activations Density 0.311%

    No Known Activations