© 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. 115473
    Prev
    Next
    INDEX
    Explanations

    ubiquitous or Uber

    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
     apprent
    -0.09
     digest
    -0.08
     Damen
    -0.08
    oice
    -0.08
     Middleton
    -0.08
     sta
    -0.08
     mut
    -0.08
    erro
    -0.08
     repl
    -0.08
     scram
    -0.07
    POSITIVE LOGITS
    itous
    0.13
     Uber
    0.12
     Ub
    0.12
     ubiqu
    0.12
    charged
    0.11
    uba
    0.11
     proto
    0.10
    itin
    0.10
    umm
    0.10
     ub
    0.10
    Activations Density 0.025%

    No Known Activations