© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 17961
    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
     wer
    -0.10
    wed
    -0.09
     vor
    -0.09
     normal
    -0.09
     synonymous
    -0.08
    ftware
    -0.08
     Wed
    -0.08
     verm
    -0.08
     Alle
    -0.08
     wed
    -0.08
    POSITIVE LOGITS
    ibe
    0.10
     Ven
    0.10
    -result
    0.09
    yd
    0.09
     statist
    0.09
     Gallagher
    0.09
    mont
    0.09
    rine
    0.09
     rte
    0.09
     Byrne
    0.09
    Activations Density 0.000%

    No Known Activations