© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    pronouns after abstract nouns

    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
    ł
    -0.10
    :<
    -0.10
    ieten
    -0.09
    gua
    -0.09
    ª
    -0.09
    aten
    -0.09
     marshal
    -0.09
    bei
    -0.09
    nown
    -0.08
     maj
    -0.08
    POSITIVE LOGITS
     you
    0.22
     they
    0.22
     we
    0.21
     it
    0.15
     she
    0.15
     he
    0.15
     THEY
    0.13
     YOU
    0.11
     I
    0.11
     someone
    0.11
    Activations Density 1.063%

    No Known Activations