© 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. 29618
    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
     undef
    -0.12
     Clo
    -0.12
     Mant
    -0.11
     Kosten
    -0.11
     Carn
    -0.11
    undle
    -0.11
     carn
    -0.10
     Pett
    -0.10
    hashed
    -0.10
    icha
    -0.10
    POSITIVE LOGITS
     pouring
    0.09
     Wine
    0.09
     errs
    0.08
    erro
    0.08
     Pour
    0.08
     mower
    0.08
     tit
    0.08
    pour
    0.07
     gob
    0.07
     gul
    0.07
    Activations Density 0.000%

    No Known Activations