© 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. 16490
    Prev
    Next
    INDEX
    Explanations

    (born date in country)

    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
     ..."↵↵
    -0.11
     ↵↵↵↵↵
    -0.11
    ewe
    -0.10
    argo
    -0.10
    ibu
    -0.10
    ,",
    -0.09
     ):
    -0.09
    illac
    -0.09
    many
    -0.09
     Schw
    -0.09
    POSITIVE LOGITS
    ........................
    0.09
    &
    0.08
    strup
    0.08
    -cond
    0.08
    _(
    0.08
    ::*
    0.08
     dire
    0.08
    Lite
    0.08
     pylint
    0.07
    âĤ¬“
    0.07
    Activations Density 0.454%

    No Known Activations