© 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. 88677
    Prev
    Next
    INDEX
    Explanations

    clinical interventions randomized flow requirements

    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
     enrich
    -0.12
     garn
    -0.12
     enrichment
    -0.11
     LGBTQ
    -0.10
     rust
    -0.09
     uranium
    -0.09
     Arcade
    -0.09
    oui
    -0.09
     urn
    -0.09
     rusty
    -0.09
    POSITIVE LOGITS
     biome
    0.18
     Workout
    0.14
     tendon
    0.13
     workouts
    0.12
     optimizer
    0.12
     jel
    0.11
     forum
    0.11
     micron
    0.11
    Optimizer
    0.11
     workout
    0.11
    Activations Density 0.394%

    No Known Activations