© 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. 54826
    Prev
    Next
    INDEX
    Explanations

    eating healthy food

    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
    ents
    -0.12
    aire
    -0.11
    (food
    -0.11
    etric
    -0.11
    aat
    -0.10
    e
    -0.10
    edb
    -0.10
    errated
    -0.10
     absorbed
    -0.10
    ANCE
    -0.10
    POSITIVE LOGITS
    ying
    0.08
    <<<
    0.08
     tissue
    0.08
     walk
    0.07
    fall
    0.07
     formal
    0.07
    ied
    0.06
    027
    0.06
    IAN
    0.06
    out
    0.06
    Activations Density 0.007%

    No Known Activations