© 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. 57095
    Prev
    Next
    INDEX
    Explanations

    navigation, robotics, cycling, climate, safety

    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
    --,
    -0.10
    >>↵↵
    -0.08
     widely
    -0.08
     mit
    -0.08
    IX
    -0.08
    ix
    -0.07
    nda
    -0.07
     PLC
    -0.07
     Lair
    -0.07
     Say
    -0.07
    POSITIVE LOGITS
    rah
    0.10
    PIO
    0.09
    [sizeof
    0.09
    .ZERO
    0.09
    Âł
    0.09
    taire
    0.09
     withd
    0.09
     ../../
    0.09
    isters
    0.08
     ########################
    0.08
    Activations Density 0.022%

    No Known Activations