© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    bacterial antigens and receptors

    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
     VO
    -0.08
    annot
    -0.07
     recording
    -0.07
     processes
    -0.07
    pson
    -0.07
     [--
    -0.07
    _dropout
    -0.07
     disclaimer
    -0.07
    Modifiers
    -0.07
     controlled
    -0.07
    POSITIVE LOGITS
     stimuli
    0.20
     stimulus
    0.16
     antig
    0.13
     triggers
    0.12
    stim
    0.12
     Stim
    0.12
     triggering
    0.12
    aval
    0.11
     presentation
    0.11
     perceived
    0.11
    Activations Density 0.606%

    No Known Activations