© 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. 90070
    Prev
    Next
    INDEX
    Explanations

    may or may not, -ization, -isation

    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
     Downing
    -0.10
     circumstance
    -0.09
    .emplace
    -0.08
    -IS
    -0.08
     Rt
    -0.08
     Celt
    -0.08
     itself
    -0.08
     destruct
    -0.08
     Anthem
    -0.08
    eland
    -0.08
    POSITIVE LOGITS
    |i
    0.11
    oeff
    0.10
     proponents
    0.10
    -ranked
    0.10
    ount
    0.10
     mount
    0.09
    -mount
    0.09
     Hobby
    0.09
     SORT
    0.09
     league
    0.09
    Activations Density 0.002%

    No Known Activations