© 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. 30801
    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
     indign
    -0.10
     conditional
    -0.09
    ance
    -0.08
    uo
    -0.08
     unified
    -0.08
     foreign
    -0.08
     Glo
    -0.08
     contamination
    -0.08
    ating
    -0.07
     incub
    -0.07
    POSITIVE LOGITS
     baj
    0.11
    EMU
    0.11
    dess
    0.11
    %'↵
    0.10
    -des
    0.10
     Pul
    0.10
     bev
    0.10
    paged
    0.10
    erot
    0.10
     Encounter
    0.10
    Activations Density 0.000%

    No Known Activations