© 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. 27559
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions

    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
     suddenly
    -0.11
     Suddenly
    -0.10
    ask
    -0.10
     starting
    -0.10
    Suddenly
    -0.09
    itic
    -0.09
     IM
    -0.09
    IM
    -0.09
    ok
    -0.09
    <quote
    -0.09
    POSITIVE LOGITS
     above
    0.12
    above
    0.11
     beside
    0.11
    Bes
    0.11
     Above
    0.10
     Bes
    0.10
     Behind
    0.10
    bove
    0.10
     gram
    0.10
     weak
    0.10
    Activations Density 0.029%

    No Known Activations