© 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. 90871
    Prev
    Next
    INDEX
    Explanations

    -wise or point of view

    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
    nek
    -0.10
    ardy
    -0.10
    asp
    -0.10
    avel
    -0.09
    ware
    -0.09
     nons
    -0.09
    .newaxis
    -0.09
    adamente
    -0.09
     salt
    -0.09
    -style
    -0.09
    POSITIVE LOGITS
    ected
    0.08
     dart
    0.08
    ihan
    0.08
     interact
    0.07
     scho
    0.07
     Penn
    0.07
    Mil
    0.07
    еÑĢа
    0.07
    erts
    0.07
    manent
    0.07
    Activations Density 0.060%

    No Known Activations