© 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. 56949
    Prev
    Next
    INDEX
    Explanations

    boundary condition

    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
    ed
    -0.13
    ly
    -0.11
    ually
    -0.10
    o
    -0.09
    ernet
    -0.09
    fed
    -0.09
    als
    -0.09
    ÑĥÑĩ
    -0.09
    liness
    -0.08
    sb
    -0.08
    POSITIVE LOGITS
    iram
    0.10
    ework
    0.10
    ity
    0.10
    ä½į
    0.09
     Gloria
    0.08
    rez
    0.08
     Tub
    0.08
     Ferd
    0.08
    blick
    0.08
     irrit
    0.08
    Activations Density 0.003%

    No Known Activations