© 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. 91825
    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
     exile
    -0.07
     Abed
    -0.07
     gee
    -0.07
     uncomment
    -0.07
    Compat
    -0.07
     notch
    -0.07
     brib
    -0.07
     Kidd
    -0.07
     overd
    -0.07
     Lem
    -0.07
    POSITIVE LOGITS
     minutes
    0.12
     alo
    0.12
     mand
    0.11
    -Smith
    0.11
     Minutes
    0.11
     rotation
    0.11
    /tutorial
    0.10
     Topic
    0.10
    Bear
    0.10
    minutes
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.