© 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. 114561
    Prev
    Next
    INDEX
    Explanations

    before or after

    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
    grunt
    -0.10
    agal
    -0.09
     ske
    -0.09
     blown
    -0.09
    phis
    -0.08
     globalization
    -0.08
    sequ
    -0.08
    iator
    -0.08
     Gir
    -0.08
     cum
    -0.08
    POSITIVE LOGITS
     surfaces
    0.11
     indoors
    0.11
    abo
    0.10
    azzi
    0.10
     preferably
    0.09
    unless
    0.09
     polar
    0.09
     marble
    0.09
    mut
    0.09
     thirsty
    0.09
    Activations Density 0.096%

    No Known Activations