© 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. 27467
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

    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
    874
    -0.11
     warrants
    -0.11
     nevertheless
    -0.11
    andr
    -0.10
    fern
    -0.10
     daher
    -0.10
     anyways
    -0.10
    iasm
    -0.10
     anyway
    -0.10
     conglomer
    -0.10
    POSITIVE LOGITS
     so
    0.27
     So
    0.24
    So
    0.22
    æīĢ
    0.20
    so
    0.18
    	So
    0.14
     så
    0.14
     SO
    0.10
     soo
    0.10
     Dexter
    0.10
    Activations Density 0.334%

    No Known Activations