© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113727
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     tot
    -0.10
     unsur
    -0.10
     aka
    -0.10
     Madagascar
    -0.09
     tah
    -0.09
     dough
    -0.09
    curring
    -0.09
    utt
    -0.09
    nge
    -0.09
     Rico
    -0.09
    POSITIVE LOGITS
     anymore
    0.12
     anytime
    0.09
     gusto
    0.09
     ever
    0.08
    ever
    0.08
    ?"↵
    0.08
    ?;↵
    0.08
    ?'
    0.08
     anywhere
    0.08
     awhile
    0.07
    Activations Density 0.073%

    No Known Activations