© 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. 55525
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
     founding
    -0.10
    rome
    -0.08
    sim
    -0.08
     sim
    -0.08
     Sims
    -0.08
    resents
    -0.08
    icken
    -0.07
     Violet
    -0.07
    Sim
    -0.07
    achel
    -0.07
    POSITIVE LOGITS
    ua
    0.09
    esan
    0.09
     quel
    0.09
    lier
    0.09
    ibal
    0.09
    IFIER
    0.09
     Facial
    0.09
    quir
    0.09
    liches
    0.08
    Injected
    0.08
    Activations Density 0.029%

    No Known Activations