© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 377
    Prev
    Next
    INDEX
    Explanations

    inhibitores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invol
    -0.09
     infected
    -0.08
     strat
    -0.08
     plast
    -0.08
     insured
    -0.08
     vaccinated
    -0.08
     defe
    -0.08
     serviced
    -0.08
    odem
    -0.07
     Contrib
    -0.07
    POSITIVE LOGITS
     marketed
    0.16
     potency
    0.16
     potent
    0.14
     formulated
    0.13
     compounds
    0.13
     formulations
    0.13
     orally
    0.13
     derivatives
    0.13
     properties
    0.13
     dosage
    0.12
    Activations Density 3.838%

    No Known Activations