© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29699
    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
    ernes
    -0.11
    tright
    -0.11
    dad
    -0.11
    ysz
    -0.10
     Tops
    -0.10
     torn
    -0.10
    jis
    -0.09
    rij
    -0.09
    kees
    -0.09
    à§į
    -0.09
    POSITIVE LOGITS
     disproportion
    0.10
     Vanderbilt
    0.10
     indigenous
    0.09
     recip
    0.09
    ghost
    0.09
    å¢
    0.08
     subtly
    0.08
     grate
    0.08
    uber
    0.08
    äº
    0.08
    Activations Density 0.000%

    No Known Activations