© 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. 48594
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hug
    -0.09
     Huss
    -0.09
     Paras
    -0.08
    ukes
    -0.08
     mix
    -0.08
     Ada
    -0.08
     Geoffrey
    -0.08
     Bates
    -0.08
    bler
    -0.08
     confused
    -0.08
    POSITIVE LOGITS
    cip
    0.11
     retrospect
    0.10
    ault
    0.10
    azel
    0.10
    eneg
    0.09
    dag
    0.09
     Cent
    0.09
    دÙĬ
    0.09
    ez
    0.09
     themselves
    0.09
    Activations Density 0.000%

    No Known Activations