© 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. 31198
    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
    omit
    -0.10
    empo
    -0.10
     ..."↵↵
    -0.09
    IDA
    -0.09
     Mej
    -0.09
    onal
    -0.09
     Levin
    -0.08
    ..."↵
    -0.08
     Inches
    -0.08
     ???
    -0.08
    POSITIVE LOGITS
    uri
    0.09
     apl
    0.09
    UG
    0.09
     hap
    0.09
    636
    0.09
     Registr
    0.08
     artic
    0.08
    atz
    0.08
     hollow
    0.08
     Zub
    0.08
    Activations Density 0.000%

    No Known Activations