© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89588
    Prev
    Next
    INDEX
    Explanations

    production and synthesis

    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
     biom
    -0.10
     Reese
    -0.10
     reb
    -0.09
     Burl
    -0.09
    JR
    -0.09
     lubric
    -0.08
     struct
    -0.08
     fluids
    -0.08
     tor
    -0.08
     ìŀħ
    -0.08
    POSITIVE LOGITS
     conversion
    0.14
     Production
    0.14
     production
    0.14
     synthesis
    0.14
    -production
    0.13
    Produ
    0.13
    Production
    0.13
     ovar
    0.12
     liver
    0.12
    -producing
    0.12
    Activations Density 1.798%

    No Known Activations