© 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. 8148
    Prev
    Next
    INDEX
    Explanations

    names followed by names or titles

    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
    assen
    -0.09
     Panc
    -0.09
     Bronze
    -0.08
     Miss
    -0.08
    izes
    -0.08
     indirect
    -0.08
     Carousel
    -0.08
     BOTH
    -0.08
     LLC
    -0.08
     ocup
    -0.08
    POSITIVE LOGITS
     woke
    0.15
     vs
    0.12
     waking
    0.12
     anx
    0.12
     couldn
    0.12
     wakes
    0.12
     appreh
    0.12
     struggles
    0.12
     discovers
    0.12
     nerv
    0.11
    Activations Density 0.050%

    No Known Activations