© 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. 90553
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and court document details

    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
     gib
    -0.13
     gamm
    -0.11
    ottes
    -0.10
     Zak
    -0.10
    Sorted
    -0.09
     Vick
    -0.09
     Disconnect
    -0.09
    ..<
    -0.09
     Swap
    -0.09
     Um
    -0.09
    POSITIVE LOGITS
    vvm
    0.08
     dec
    0.08
     instant
    0.08
    bau
    0.08
     Zimmer
    0.08
    olan
    0.07
     cater
    0.07
     Gors
    0.07
     poj
    0.07
    antium
    0.07
    Activations Density 0.003%

    No Known Activations