© 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. 89917
    Prev
    Next
    INDEX
    Explanations

    exist / exists

    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
    baum
    -0.11
     ousted
    -0.11
    ocre
    -0.10
     Pearl
    -0.10
    inta
    -0.10
    474
    -0.10
     Unexpected
    -0.10
    eel
    -0.10
     indeb
    -0.10
    ichi
    -0.10
    POSITIVE LOGITS
     exist
    0.57
     exists
    0.55
     existence
    0.50
    ä¸įåŃĺåľ¨
    0.48
     Exist
    0.47
     Exists
    0.47
     existed
    0.47
    exists
    0.46
     nonexistent
    0.43
     existe
    0.42
    Activations Density 0.738%

    No Known Activations