© 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. 57578
    Prev
    Next
    INDEX
    Explanations

    nanomaterials, micromachines, sensors, molecules

    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
    zek
    -0.11
    chai
    -0.10
    alchemy
    -0.10
    -ie
    -0.10
    imits
    -0.10
    afb
    -0.10
    coat
    -0.09
     Deadly
    -0.09
    (ob
    -0.09
    .Bad
    -0.09
    POSITIVE LOGITS
     Dro
    0.07
     Clyde
    0.06
     Gre
    0.06
     swingers
    0.06
     Ill
    0.06
     blocks
    0.06
     santa
    0.06
     Malk
    0.06
     gre
    0.06
    /function
    0.06
    Activations Density 0.002%

    No Known Activations