© 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. 116610
    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
     Wo
    -0.10
    -us
    -0.10
    ivi
    -0.09
     Wander
    -0.09
    -Sah
    -0.09
    -anchor
    -0.09
     Rid
    -0.09
    Carthy
    -0.09
    aras
    -0.09
     Burl
    -0.08
    POSITIVE LOGITS
     lum
    0.11
     trouble
    0.10
     imper
    0.10
     freely
    0.09
    indre
    0.09
    ech
    0.09
    ches
    0.09
     cav
    0.09
    Dock
    0.09
    umped
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.