© 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. 17430
    Prev
    Next
    INDEX
    Explanations

    blogging software or men's tournaments

    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
    anz
    -0.10
    anian
    -0.10
    annt
    -0.10
     Wonderland
    -0.10
     Eag
    -0.10
    lish
    -0.09
    serde
    -0.09
    ,#
    -0.09
    .clip
    -0.09
     proudly
    -0.09
    POSITIVE LOGITS
     mend
    0.09
     conc
    0.08
     Hag
    0.08
     reinc
    0.08
     terra
    0.08
     rut
    0.08
     exe
    0.08
     Tit
    0.08
    !!)↵
    0.08
    :↵
    0.07
    Activations Density 0.001%

    No Known Activations