© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58128
    Prev
    Next
    INDEX
    Explanations

    defined, studies, debate

    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
     diagnosis
    -0.11
     diagnostic
    -0.10
     prevalence
    -0.10
     medically
    -0.09
     filmy
    -0.09
     enr
    -0.09
     diagnoses
    -0.09
     diagn
    -0.09
     using
    -0.09
     Guinness
    -0.09
    POSITIVE LOGITS
     debate
    0.11
     debated
    0.10
     debates
    0.10
     Argument
    0.10
     Arguments
    0.10
     Debate
    0.10
     arg
    0.09
    Argument
    0.08
     Intermediate
    0.08
     Chamber
    0.08
    Activations Density 0.073%

    No Known Activations