© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14001
    Prev
    Next
    INDEX
    Explanations

    parts moving or transitioning

    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
    Negative Logits
     ceremonial
    -0.08
     alongside
    -0.07
     dici
    -0.07
     amidst
    -0.07
     puff
    -0.07
    jected
    -0.07
    fal
    -0.07
    MAND
    -0.07
     pel
    -0.07
    mouth
    -0.07
    POSITIVE LOGITS
    esser
    0.10
     sandbox
    0.10
     cuckold
    0.09
     hass
    0.09
     nag
    0.09
     Bolton
    0.09
    vod
    0.09
     Cout
    0.09
    nde
    0.09
    "class
    0.09
    Activations Density 0.533%

    No Known Activations