© 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. 50097
    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
     Daisy
    -0.11
     synchronized
    -0.09
     circulating
    -0.08
     con
    -0.08
     ph
    -0.08
     integ
    -0.08
    ischer
    -0.08
     dy
    -0.08
     circulation
    -0.08
     Diamond
    -0.07
    POSITIVE LOGITS
    bread
    0.11
    Inactive
    0.10
    elden
    0.10
     sach
    0.10
     stem
    0.10
     Homepage
    0.10
     Stem
    0.10
    -validate
    0.10
     Hayden
    0.09
    itm
    0.09
    Activations Density 0.000%

    No Known Activations