© 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. 116992
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
     incoming
    -0.11
    Incoming
    -0.10
    321
    -0.10
    fra
    -0.09
    bris
    -0.09
    lav
    -0.09
    chas
    -0.09
    inis
    -0.09
    fi
    -0.09
    Incre
    -0.09
    POSITIVE LOGITS
    /out
    0.19
    coe
    0.10
    ,out
    0.10
     Kul
    0.10
    -Out
    0.10
    ufe
    0.09
     supp
    0.09
    woods
    0.09
    -out
    0.09
     punt
    0.09
    Activations Density 0.067%

    No Known Activations