© 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. 34152
    Prev
    Next
    INDEX
    Explanations

    removal and replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     withdrawn
    -0.12
     ku
    -0.12
    contro
    -0.12
    elim
    -0.11
    esch
    -0.11
    meno
    -0.11
    Withdraw
    -0.11
     hoops
    -0.11
     elim
    -0.11
    uda
    -0.11
    POSITIVE LOGITS
     replaced
    0.13
     replace
    0.11
     lay
    0.10
     replacing
    0.10
     stored
    0.10
     put
    0.10
     placed
    0.09
     tossed
    0.09
    Replacing
    0.09
     exposing
    0.08
    Activations Density 0.055%

    No Known Activations