© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    language names and articles

    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
    agt
    -0.11
    ister
    -0.11
     cann
    -0.10
    tps
    -0.09
     directions
    -0.09
    ppt
    -0.09
     Recon
    -0.09
    ez
    -0.09
     preach
    -0.09
    ptr
    -0.09
    POSITIVE LOGITS
     arbitrary
    0.09
     item
    0.08
     Feinstein
    0.08
     material
    0.08
     Olsen
    0.08
     Arbitrary
    0.08
    -any
    0.08
    words
    0.07
    ä»»
    0.07
     Existing
    0.07
    Activations Density 0.006%

    No Known Activations