© 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. 113500
    Prev
    Next
    INDEX
    Explanations

    already lined up, catch, may be, prefer to, no broker

    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
    ..↵
    -0.13
    ..↵↵
    -0.12
     equipments
    -0.11
     ..↵↵
    -0.11
    .."
    -0.10
     atleast
    -0.10
    "..
    -0.10
     jus
    -0.10
     Whilst
    -0.09
    ..
    -0.09
    POSITIVE LOGITS
     OK
    0.16
     ÂŃ
    0.14
    -ish
    0.13
     ["
    0.13
     [...]
    0.13
     info
    0.13
     —
    0.13
    -plus
    0.13
    [,]
    0.12
     [
    0.12
    Activations Density 0.031%

    No Known Activations