© 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. 5205
    Prev
    Next
    INDEX
    Explanations

    while + state or clause

    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
     Ging
    -0.11
    phan
    -0.10
    umi
    -0.10
     Adler
    -0.10
    /gui
    -0.10
     gotta
    -0.10
     stray
    -0.09
    AAD
    -0.09
    -prop
    -0.09
     Liebe
    -0.09
    POSITIVE LOGITS
     underway
    0.11
     they
    0.11
     youre
    0.11
     working
    0.10
     you
    0.09
    ski
    0.09
     undergoing
    0.09
     attempting
    0.09
     she
    0.09
     driving
    0.08
    Activations Density 0.028%

    No Known Activations