© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    pronouns and reciprocal relations

    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
    ¥
    -0.10
     sscanf
    -0.09
    mare
    -0.09
     Hue
    -0.09
    uez
    -0.09
    /Index
    -0.09
    .);↵
    -0.09
    resse
    -0.09
    ahu
    -0.09
    atte
    -0.09
    POSITIVE LOGITS
     latter
    0.13
     himself
    0.11
    him
    0.10
     vice
    0.09
     Together
    0.09
     whom
    0.08
     symb
    0.08
     mutual
    0.08
     friendship
    0.08
    Together
    0.08
    Activations Density 0.198%

    No Known Activations