© 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. 56960
    Prev
    Next
    INDEX
    Explanations

    developed, created, devised, launched

    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
     a
    -0.14
    ä¸Ģ个
    -0.10
     an
    -0.10
     Pond
    -0.10
     someone
    -0.09
     ann
    -0.09
     something
    -0.09
     somebody
    -0.09
     fare
    -0.09
     sina
    -0.09
    POSITIVE LOGITS
    mach
    0.09
     Woj
    0.08
    oz
    0.08
     Tri
    0.08
    (.
    0.08
    gow
    0.08
     Broncos
    0.08
     bras
    0.08
    .package
    0.08
    inyin
    0.08
    Activations Density 0.091%

    No Known Activations