© 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. 91001
    Prev
    Next
    INDEX
    Explanations

    MultiGraph, Challenger 2, 2010

    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
     prolifer
    -0.09
     prelim
    -0.08
    Manifest
    -0.08
     Rae
    -0.08
    -exclusive
    -0.08
     curated
    -0.08
     Plum
    -0.08
     Serena
    -0.08
     Setter
    -0.08
    igi
    -0.07
    POSITIVE LOGITS
     nett
    0.10
     w
    0.10
    [âĢ¦]
    0.09
     Composer
    0.09
     Vale
    0.09
     fri
    0.09
    isko
    0.09
    ÂĢÂĻ
    0.09
     coins
    0.09
     «
    0.09
    Activations Density 0.024%

    No Known Activations