© 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. 4672
    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
    sey
    -0.09
     LOSS
    -0.09
     sympath
    -0.09
     Hobby
    -0.09
    elay
    -0.09
     pronto
    -0.08
    shell
    -0.08
     Hann
    -0.08
     sadd
    -0.08
    ugh
    -0.08
    POSITIVE LOGITS
     MEP
    0.09
     Fus
    0.09
    ipes
    0.09
     Dedicated
    0.09
    enÃŃ
    0.08
    Danny
    0.08
     topLevel
    0.08
    ?,
    0.08
     alist
    0.08
    leon
    0.08
    Activations Density 0.000%

    No Known Activations