© 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. 33074
    Prev
    Next
    INDEX
    Explanations

    NY / MIT / interstate

    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
     segreg
    -0.10
    ki
    -0.09
     Moss
    -0.09
     Laguna
    -0.09
    ..'
    -0.09
    vero
    -0.08
    nde
    -0.08
     Mast
    -0.08
     hypoth
    -0.08
    LOT
    -0.08
    POSITIVE LOGITS
     Dart
    0.10
    lint
    0.10
     Hog
    0.09
    conv
    0.09
     dart
    0.09
    Conv
    0.09
    ilda
    0.09
     egregious
    0.09
     interstate
    0.09
    agra
    0.09
    Activations Density 0.039%

    No Known Activations