© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112951
    Prev
    Next
    INDEX
    Explanations

    pronoun verb pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owo
    -0.11
    ODB
    -0.10
     wouldn
    -0.10
    jn
    -0.10
    PEC
    -0.10
    677
    -0.10
    uler
    -0.10
    ARGET
    -0.10
     Gim
    -0.09
     Sho
    -0.09
    POSITIVE LOGITS
     presently
    0.11
     lul
    0.09
    /we
    0.09
     myster
    0.08
     admittedly
    0.08
    emble
    0.08
     currently
    0.08
     CURRENT
    0.08
    izzle
    0.08
     unint
    0.08
    Activations Density 0.074%

    No Known Activations