© 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. 26897
    Prev
    Next
    INDEX
    Explanations

    expert names and titles

    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
     donors
    -0.11
    chin
    -0.10
     asc
    -0.10
     Wife
    -0.08
     UIP
    -0.08
    wap
    -0.08
    ror
    -0.08
    steller
    -0.08
     cog
    -0.08
    ´
    -0.08
    POSITIVE LOGITS
     certified
    0.16
     experts
    0.16
     Certified
    0.14
     expert
    0.14
     Experts
    0.14
     Expert
    0.13
     recommends
    0.13
    -cert
    0.13
    expert
    0.12
    Experts
    0.12
    Activations Density 0.103%

    No Known Activations