© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    M16, E-field, MBC, T2D, M6G

    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
    e
    -0.17
    i
    -0.16
    t
    -0.16
    r
    -0.16
    y
    -0.15
    a
    -0.15
    l
    -0.14
    u
    -0.13
    o
    -0.13
    c
    -0.13
    POSITIVE LOGITS
    /o
    0.11
    usterity
    0.10
    -motion
    0.09
    quis
    0.09
    noinspection
    0.09
    quisition
    0.09
    inte
    0.08
    Ì
    0.08
     Spotlight
    0.08
    weise
    0.08
    Activations Density 3.581%

    No Known Activations