© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 111878
    Prev
    Next
    INDEX
    Explanations

    conjunction "so"

    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
    —it
    -0.09
    —an
    -0.09
    Reflection
    -0.08
    Watching
    -0.08
     watching
    -0.08
    —a
    -0.08
     cooper
    -0.08
    —I
    -0.08
     Likely
    -0.08
     interoper
    -0.08
    POSITIVE LOGITS
    So
    0.29
     So
    0.29
    .So
    0.21
     so
    0.20
     Don
    0.20
    	So
    0.19
    Don
    0.19
    æīĢ
    0.18
    _so
    0.17
    .so
    0.16
    Activations Density 0.091%

    No Known Activations