© 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. 112923
    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
     discre
    -0.10
    antz
    -0.10
     Dent
    -0.10
    839
    -0.09
     requis
    -0.09
     MSR
    -0.09
    gan
    -0.09
    841
    -0.09
    omes
    -0.09
    hunter
    -0.09
    POSITIVE LOGITS
     Voll
    0.10
    ...',↵
    0.09
    Resources
    0.09
    /resources
    0.09
     humili
    0.08
     sil
    0.08
     misuse
    0.08
     oversh
    0.08
    akan
    0.08
     humiliation
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.