© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    miles, km, speed, weight

    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
     kale
    -0.10
     eta
    -0.10
    TOT
    -0.09
    issy
    -0.09
     segue
    -0.09
    igo
    -0.09
    =}
    -0.09
    omorphic
    -0.09
    ERT
    -0.09
    oodles
    -0.09
    POSITIVE LOGITS
    amon
    0.09
     wonder
    0.08
    /im
    0.08
     Glas
    0.07
    redit
    0.07
     PURE
    0.07
    ¡
    0.07
     Mont
    0.07
    uple
    0.07
     Lo
    0.07
    Activations Density 0.074%

    No Known Activations