© 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. 50531
    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
     dam
    -0.11
     Alam
    -0.11
    ieder
    -0.11
    åĬŁ
    -0.11
     guarantees
    -0.10
     Warn
    -0.10
     Guar
    -0.10
     Trilogy
    -0.10
    olic
    -0.10
    ä¿Ŀ
    -0.10
    POSITIVE LOGITS
     absolutely
    0.09
     bitterness
    0.09
     absolut
    0.09
    safe
    0.09
     saf
    0.08
    uner
    0.08
    Unsafe
    0.08
     selectively
    0.08
    afa
    0.08
     safest
    0.07
    Activations Density 0.000%

    No Known Activations