© 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. 46640
    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
     cir
    -0.10
    etime
    -0.09
    fully
    -0.09
    asm
    -0.08
    eries
    -0.08
     Roth
    -0.08
    aul
    -0.08
    ician
    -0.08
    mue
    -0.08
    nst
    -0.08
    POSITIVE LOGITS
     savedInstanceState
    0.18
    .Bundle
    0.13
    /package
    0.13
     pack
    0.12
     bundle
    0.12
    (bundle
    0.11
    (Bundle
    0.11
     tightly
    0.11
     bundles
    0.11
    bundles
    0.11
    Activations Density 0.028%

    No Known Activations