© 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. 97
    Prev
    Next
    INDEX
    Explanations

    bloodstream infection

    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
    ola
    -0.10
    fire
    -0.09
    oy
    -0.09
    istic
    -0.09
    wood
    -0.09
    work
    -0.09
    ally
    -0.09
    ort
    -0.09
    ur
    -0.08
     scape
    -0.08
    POSITIVE LOGITS
    edly
    0.16
    ers
    0.14
    mitter
    0.13
    /down
    0.13
    ters
    0.12
    ting
    0.12
    igans
    0.11
    ingt
    0.11
    enment
    0.11
    мен
    0.10
    Activations Density 3.254%

    No Known Activations