© 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. 117165
    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
    LEAR
    -0.10
     campaigners
    -0.09
    older
    -0.09
    ique
    -0.09
     preached
    -0.09
     Clay
    -0.08
    -major
    -0.08
    sher
    -0.08
     Aad
    -0.08
     unfinished
    -0.08
    POSITIVE LOGITS
    vro
    0.10
    ajo
    0.10
     therein
    0.09
     Dress
    0.09
     expos
    0.09
    avy
    0.09
    reas
    0.09
    rade
    0.09
     left
    0.09
    ourt
    0.09
    Activations Density 0.000%

    No Known Activations