© 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. 16457
    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
     Tib
    -0.10
     topo
    -0.09
     bust
    -0.09
    esch
    -0.09
    eker
    -0.09
    idis
    -0.09
     @$
    -0.09
    plementation
    -0.09
     erb
    -0.09
    aupt
    -0.09
    POSITIVE LOGITS
     Ki
    0.11
     Dam
    0.10
     Thorn
    0.10
     Ros
    0.09
    Ki
    0.09
    cosa
    0.09
     Borg
    0.09
    .ie
    0.09
    exo
    0.09
     ki
    0.09
    Activations Density 0.000%

    No Known Activations