© 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. 47346
    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
     parked
    -0.13
     Downing
    -0.11
    ylon
    -0.11
     eventual
    -0.11
     latency
    -0.10
     Scoped
    -0.10
    edd
    -0.10
     Guil
    -0.10
    lique
    -0.10
     Kinder
    -0.10
    POSITIVE LOGITS
    loh
    0.08
    iar
    0.08
     premium
    0.08
    sic
    0.07
     Zu
    0.07
     Tos
    0.07
     sweetheart
    0.07
     crown
    0.07
    premium
    0.07
     zus
    0.07
    Activations Density 0.000%

    No Known Activations