© 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. 5404
    Prev
    Next
    INDEX
    Explanations

    injection and infusion administration

    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
     Helmet
    -0.12
     grat
    -0.11
     grooming
    -0.11
     helmet
    -0.10
     toll
    -0.10
     Dich
    -0.10
     organ
    -0.10
     resc
    -0.09
     groom
    -0.09
     tumble
    -0.09
    POSITIVE LOGITS
     injection
    0.51
     inject
    0.49
     injections
    0.48
     injecting
    0.47
     injected
    0.46
     Injection
    0.45
     Inject
    0.44
     injector
    0.40
    Inject
    0.38
    Injection
    0.38
    Activations Density 0.951%

    No Known Activations