© 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. 5510
    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
    zilla
    -0.10
     Swan
    -0.09
     exagger
    -0.09
    Named
    -0.09
     abort
    -0.09
    idy
    -0.09
    elo
    -0.09
    ee
    -0.09
     manip
    -0.09
    orda
    -0.08
    POSITIVE LOGITS
    cent
    0.11
    /out
    0.09
    /cop
    0.08
     Cooper
    0.08
    /by
    0.08
     busted
    0.08
     Aviv
    0.08
     Vick
    0.08
     ivory
    0.08
    ér
    0.08
    Activations Density 0.000%

    No Known Activations