© 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. 6038
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
     bluff
    -0.08
    loo
    -0.08
    apis
    -0.08
     Toll
    -0.08
    oes
    -0.08
     Declarations
    -0.08
     Overnight
    -0.07
     Biological
    -0.07
    isode
    -0.07
    andel
    -0.07
    POSITIVE LOGITS
     ago
    0.18
    ago
    0.15
     Ago
    0.14
     months
    0.13
    Months
    0.13
    months
    0.11
    opo
    0.11
     years
    0.11
     olds
    0.11
    _months
    0.11
    Activations Density 0.011%

    No Known Activations