© 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. 89938
    Prev
    Next
    INDEX
    Explanations

    people and places

    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
     concurrently
    -0.11
     handed
    -0.11
    Opened
    -0.10
    -disabled
    -0.10
     unborn
    -0.10
    endi
    -0.10
     outs
    -0.10
     å·
    -0.10
     dak
    -0.10
     concurrent
    -0.10
    POSITIVE LOGITS
     Wire
    0.08
     bachelor
    0.08
     still
    0.08
    ayar
    0.08
    .Unity
    0.07
     Syracuse
    0.07
     AJ
    0.07
    yll
    0.07
     Aj
    0.07
    qua
    0.07
    Activations Density 0.029%

    No Known Activations