© 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. 600
    Prev
    Next
    INDEX
    Explanations

    noun phrases following 'the'

    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
     and
    -0.11
     the
    -0.11
    (
    -0.10
     with
    -0.10
    ,
    -0.09
     which
    -0.08
     anew
    -0.08
    .
    -0.08
    /b
    -0.08
    led
    -0.07
    POSITIVE LOGITS
    ses
    0.26
     same
    0.24
     entirety
    0.23
     entire
    0.21
     aforementioned
    0.20
     rest
    0.20
    sse
    0.18
    irs
    0.17
     likes
    0.17
     following
    0.17
    Activations Density 3.369%

    No Known Activations