© 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. 28832
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by auxiliary 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
    itel
    -0.10
     fon
    -0.09
    fty
    -0.09
     scaling
    -0.08
    iform
    -0.08
    imi
    -0.08
    ied
    -0.08
    ifu
    -0.08
     Michele
    -0.07
    iten
    -0.07
    POSITIVE LOGITS
    upon
    0.13
     sham
    0.11
     concerned
    0.10
    nee
    0.10
    bbe
    0.10
    owitz
    0.10
    prep
    0.10
    Ver
    0.10
    hog
    0.10
    aat
    0.10
    Activations Density 0.046%

    No Known Activations