© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 14920
    Prev
    Next
    INDEX
    Explanations

    examples, such as "amount of" or "you should"

    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
     samt
    -0.13
     sobie
    -0.12
     filles
    -0.12
     Bayer
    -0.11
     ®
    -0.11
     datatype
    -0.11
     caucus
    -0.11
    )$/
    -0.11
     &#
    -0.11
     Lance
    -0.11
    POSITIVE LOGITS
     vivastreet
    0.12
    ..."
    0.08
    ..."↵↵
    0.07
     pog
    0.07
    ...",
    0.07
     tud
    0.07
    ...</
    0.07
    .↵↵↵↵↵
    0.07
    ...↵↵
    0.07
     visite
    0.06
    Activations Density 0.582%

    No Known Activations