© 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. 4485
    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
     those
    -0.10
     my
    -0.10
     our
    -0.10
     esos
    -0.09
     aquel
    -0.08
     Those
    -0.08
     nuestras
    -0.08
    itur
    -0.08
    empt
    -0.08
    egl
    -0.07
    POSITIVE LOGITS
     a
    0.16
     an
    0.15
     specially
    0.15
    ä¸Ģ个
    0.14
     several
    0.14
    Various
    0.12
     nearby
    0.12
     twin
    0.12
     various
    0.11
     two
    0.11
    Activations Density 1.315%

    No Known Activations