© 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. 32317
    Prev
    Next
    INDEX
    Explanations

    founder and CEO

    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
     assistants
    -0.12
     subordinate
    -0.12
    assistant
    -0.11
    Assistant
    -0.10
     aide
    -0.10
     specialists
    -0.10
     Specialist
    -0.10
     delegates
    -0.10
    Delegate
    -0.10
     cad
    -0.10
    POSITIVE LOGITS
     founder
    0.39
     Founder
    0.31
     founding
    0.31
     founders
    0.30
    Founder
    0.27
     creator
    0.25
    -founder
    0.24
     founded
    0.23
     cof
    0.21
     co
    0.21
    Activations Density 0.801%

    No Known Activations