© 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. 18433
    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
    wed
    -0.11
     Coh
    -0.10
     sleeper
    -0.10
     kao
    -0.10
     tasted
    -0.10
     обÑĬ
    -0.10
     jewel
    -0.09
     hud
    -0.09
    uber
    -0.09
    igin
    -0.09
    POSITIVE LOGITS
    urr
    0.09
     site
    0.09
     Fur
    0.09
     Blanch
    0.09
     Pey
    0.09
    cred
    0.08
    retch
    0.08
    site
    0.08
    nement
    0.08
     segregated
    0.08
    Activations Density 0.000%

    No Known Activations