© 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. 114768
    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
    ioni
    -0.10
     gaz
    -0.10
     CCC
    -0.09
     Cros
    -0.09
     Staten
    -0.09
     Gazette
    -0.09
    MASK
    -0.09
     rejo
    -0.09
     annunci
    -0.09
     tableau
    -0.09
    POSITIVE LOGITS
     cog
    0.10
    vf
    0.09
     metaphor
    0.09
     mod
    0.09
     exhausted
    0.09
    rog
    0.09
     moder
    0.09
     forever
    0.08
     coff
    0.08
     Scot
    0.08
    Activations Density 0.000%

    No Known Activations