© 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. 88125
    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
     plead
    -0.08
    verts
    -0.08
    ..↵↵↵↵
    -0.08
     sway
    -0.08
     sworn
    -0.08
    ÙĦا
    -0.08
     mee
    -0.08
     mour
    -0.07
     Woodward
    -0.07
    bij
    -0.07
    POSITIVE LOGITS
     knowingly
    0.11
     SCAN
    0.11
    chan
    0.11
    isters
    0.10
    Govern
    0.10
     Ramp
    0.10
    771
    0.10
    obl
    0.10
    .live
    0.10
    еб
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.