© 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. 88184
    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
    rawer
    -0.11
     Hull
    -0.11
    steen
    -0.10
     hull
    -0.10
    inki
    -0.10
    chooser
    -0.10
    á»ĵ
    -0.10
    abile
    -0.10
    hung
    -0.09
    価
    -0.09
    POSITIVE LOGITS
     borrowing
    0.09
     Kraft
    0.09
    /wiki
    0.08
     Olson
    0.08
    kal
    0.08
     sce
    0.08
     Barnett
    0.08
     deb
    0.08
     Rankings
    0.08
     Synd
    0.07
    Activations Density 0.000%

    No Known Activations