© 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. 112076
    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
     enjo
    -0.10
    iman
    -0.09
    /man
    -0.09
    yan
    -0.08
    olib
    -0.08
    fort
    -0.08
    umar
    -0.08
     exter
    -0.08
    atus
    -0.08
    )throws
    -0.08
    POSITIVE LOGITS
     Publications
    0.10
     Darling
    0.09
     crossing
    0.09
    illet
    0.09
     Gef
    0.09
    ouro
    0.09
     Documentation
    0.09
     recently
    0.09
     Geneva
    0.09
     budding
    0.09
    Activations Density 0.000%

    No Known Activations