© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    horse race

    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
     sworn
    -0.10
     Human
    -0.08
     cod
    -0.08
    unker
    -0.07
     Frozen
    -0.07
    unk
    -0.07
    Regions
    -0.07
     sustainability
    -0.07
    UCE
    -0.07
    ent
    -0.07
    POSITIVE LOGITS
     racing
    0.11
     bred
    0.11
     owners
    0.10
    hoa
    0.10
     campaigned
    0.10
     race
    0.10
    /cat
    0.10
    quin
    0.10
    amax
    0.10
     synonyms
    0.10
    Activations Density 0.050%

    No Known Activations