© 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. 115888
    Prev
    Next
    INDEX
    Explanations

    pronoun or determiner after comma

    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
     moreover
    -0.18
     furthermore
    -0.14
     meantime
    -0.11
     meanwhile
    -0.11
     then
    -0.11
     HOWEVER
    -0.10
    utas
    -0.10
     ETA
    -0.09
     thereafter
    -0.09
     comparatively
    -0.09
    POSITIVE LOGITS
     Majority
    0.10
     Walton
    0.09
    agen
    0.09
     alot
    0.09
     showcases
    0.09
    agi
    0.09
     decided
    0.09
     sporting
    0.08
    ;
    0.08
    they
    0.08
    Activations Density 0.096%

    No Known Activations