© 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. 32121
    Prev
    Next
    INDEX
    Explanations

    existential or state of being

    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
     unlikely
    -0.08
     thirsty
    -0.08
    oks
    -0.07
     ENT
    -0.07
     iframe
    -0.07
     bel
    -0.07
     beacon
    -0.07
     originally
    -0.07
     Py
    -0.07
     tired
    -0.07
    POSITIVE LOGITS
     abound
    0.18
     outweigh
    0.14
     exist
    0.14
     flourish
    0.14
     occur
    0.13
     exists
    0.13
     intensified
    0.13
     apl
    0.13
     vorhand
    0.12
     abundance
    0.12
    Activations Density 0.936%

    No Known Activations