© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48591
    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
     Safe
    -0.09
    .rel
    -0.09
    dee
    -0.09
    afe
    -0.09
    nik
    -0.08
     chrome
    -0.08
    ensa
    -0.08
    nett
    -0.08
    ran
    -0.08
     aest
    -0.08
    POSITIVE LOGITS
     gaz
    0.09
    irl
    0.09
    arak
    0.09
    fila
    0.09
    akra
    0.09
     exempl
    0.09
    usher
    0.09
    å¸ĥ
    0.09
    bst
    0.08
     headline
    0.08
    Activations Density 0.000%

    No Known Activations