© 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. 114327
    Prev
    Next
    INDEX
    Explanations

    numeric or address information

    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
    amber
    -0.12
     creeping
    -0.11
     dup
    -0.11
    ADDING
    -0.11
    ippets
    -0.11
     Wie
    -0.10
     conten
    -0.10
    WRAPPER
    -0.10
     Letter
    -0.10
    TITLE
    -0.10
    POSITIVE LOGITS
     dates
    0.12
     followed
    0.11
     underneath
    0.10
     date
    0.10
     paren
    0.10
     numbers
    0.09
     beneath
    0.09
     gib
    0.08
     numeric
    0.08
     directions
    0.08
    Activations Density 0.181%

    No Known Activations