© 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. 32878
    Prev
    Next
    INDEX
    Explanations

    acts as a / serves as a

    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
    atsu
    -0.12
    //(
    -0.11
     Nixon
    -0.10
     AP
    -0.10
    ICON
    -0.10
    rv
    -0.10
    -Based
    -0.10
    ей
    -0.09
     Companion
    -0.09
     Somebody
    -0.09
    POSITIVE LOGITS
     for
    0.16
     длÑı
    0.14
     für
    0.11
     bagi
    0.11
    	for
    0.10
    for
    0.10
     dafür
    0.09
     fot
    0.09
     dla
    0.09
     unto
    0.09
    Activations Density 0.344%

    No Known Activations