© 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. 115972
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verb

    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
     aqu
    -0.08
     Alf
    -0.08
     Alam
    -0.08
     correlated
    -0.07
    ade
    -0.07
     Eag
    -0.07
     tailor
    -0.07
     indicative
    -0.07
     Lomb
    -0.07
     pap
    -0.07
    POSITIVE LOGITS
     thus
    0.15
     mobil
    0.12
    thus
    0.12
     nevertheless
    0.12
     moreover
    0.11
     resume
    0.11
     resumes
    0.11
    rous
    0.11
     enrich
    0.11
     therefore
    0.11
    Activations Density 0.110%

    No Known Activations