© 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. 57138
    Prev
    Next
    INDEX
    Explanations

    cholesterol, triglycerides, hormones, lipids

    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
     thresholds
    -0.07
     periodically
    -0.07
    tem
    -0.07
     Nearby
    -0.07
     vo
    -0.07
     frat
    -0.07
     temper
    -0.07
    eor
    -0.06
     smash
    -0.06
    ROW
    -0.06
    POSITIVE LOGITS
     educ
    0.10
     Concat
    0.10
     Md
    0.10
    ño
    0.10
    Pause
    0.09
    .Escape
    0.09
    icode
    0.09
    aves
    0.09
    -total
    0.09
     UserModel
    0.09
    Activations Density 0.051%

    No Known Activations