© 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. 116206
    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
     McB
    -0.10
    DV
    -0.09
     Bravo
    -0.09
     jab
    -0.08
    -ever
    -0.08
     dov
    -0.08
     printed
    -0.08
     Riv
    -0.08
    DN
    -0.08
     Olson
    -0.08
    POSITIVE LOGITS
    GD
    0.11
    gd
    0.10
    vio
    0.10
    ercul
    0.09
    bundle
    0.09
     Glam
    0.09
     Elias
    0.09
     prematurely
    0.09
     Sext
    0.09
     feas
    0.09
    Activations Density 0.000%

    No Known Activations