© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by actions

    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
     hod
    -0.11
    udo
    -0.10
     Hod
    -0.10
    Org
    -0.10
    od
    -0.09
     compliment
    -0.09
    aq
    -0.09
     familiar
    -0.09
     belonged
    -0.09
    ugo
    -0.09
    POSITIVE LOGITS
     admittedly
    0.09
    angel
    0.09
    osome
    0.09
     imagin
    0.08
     Mor
    0.08
     trenches
    0.08
    anja
    0.08
     invis
    0.08
     Gott
    0.08
    716
    0.08
    Activations Density 0.357%

    No Known Activations