© 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. 18564
    Prev
    Next
    INDEX
    Explanations

    find local

    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
    rios
    -0.12
     ath
    -0.11
     sperma
    -0.10
     Spotlight
    -0.09
    -Semit
    -0.09
     cuck
    -0.09
     Stern
    -0.09
     Seoul
    -0.09
     Alternate
    -0.09
     consequential
    -0.09
    POSITIVE LOGITS
     local
    0.17
     Local
    0.13
     nearby
    0.13
     locally
    0.13
    local
    0.12
     LOCAL
    0.12
    Local
    0.11
     top
    0.10
     verified
    0.10
     thousands
    0.10
    Activations Density 0.016%

    No Known Activations