© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58665
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by 's or is

    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
    witter
    -0.12
    ADED
    -0.11
     Saul
    -0.11
    .mods
    -0.11
    rema
    -0.11
    onga
    -0.11
    ms
    -0.11
    ader
    -0.11
    ANTE
    -0.11
    gor
    -0.10
    POSITIVE LOGITS
     friend
    0.06
     nonetheless
    0.06
     vis
    0.05
     starting
    0.05
    Ц
    0.05
     vi
    0.05
    uffle
    0.05
     ($(
    0.05
    -prom
    0.05
    vi
    0.05
    Activations Density 0.149%

    No Known Activations