© 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. 31
    Prev
    Next
    INDEX
    Explanations

    triglyceride or tristate

    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
    -0.11
    row
    -0.10
    itra
    -0.09
    hra
    -0.08
    rices
    -0.08
    /trunk
    -0.08
    tra
    -0.07
    tron
    -0.07
    District
    -0.07
     trembling
    -0.07
    POSITIVE LOGITS
    odash
    0.14
    worthy
    0.13
    /false
    0.12
    pez
    0.12
    itionally
    0.12
    erras
    0.11
    istine
    0.11
    alles
    0.11
    door
    0.10
    doors
    0.10
    Activations Density 0.905%

    No Known Activations