© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
     nipples
    -0.11
     envis
    -0.11
     lÃł
    -0.09
    -visible
    -0.09
    unan
    -0.09
    ck
    -0.09
     suce
    -0.09
    bol
    -0.09
    have
    -0.09
     Has
    -0.09
    POSITIVE LOGITS
     entirety
    0.09
     <$
    0.09
     Ses
    0.09
    iner
    0.09
     interact
    0.08
     âĪ
    0.08
     interacts
    0.08
     hung
    0.08
    /her
    0.08
    /she
    0.08
    Activations Density 0.057%

    No Known Activations