© 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. 26180
    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
     breeze
    -0.09
     recl
    -0.09
     Hick
    -0.09
     Amber
    -0.09
     roam
    -0.09
    amba
    -0.09
     Whit
    -0.08
    iken
    -0.08
    itchen
    -0.08
     SQLITE
    -0.08
    POSITIVE LOGITS
     Fool
    0.12
    enda
    0.09
    abus
    0.09
     Jak
    0.09
    Payload
    0.09
    azzi
    0.09
     evangel
    0.09
     compress
    0.09
     award
    0.09
     BJ
    0.09
    Activations Density 0.000%

    No Known Activations