© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33554
    Prev
    Next
    INDEX
    Explanations

    to form, guide, create

    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
     widow
    -0.10
     plugged
    -0.09
    oli
    -0.09
    ض
    -0.09
     Opens
    -0.09
     fist
    -0.08
    nung
    -0.08
     tipping
    -0.08
    %\
    -0.08
    lush
    -0.08
    POSITIVE LOGITS
     essentially
    0.11
     makeshift
    0.11
     resemble
    0.10
    ess
    0.10
    å½¢
    0.10
     resembles
    0.10
     quasi
    0.09
     Sok
    0.09
     dul
    0.09
     creating
    0.09
    Activations Density 0.138%

    No Known Activations