© 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. 111482
    Prev
    Next
    INDEX
    Explanations

    happy to help or obliged

    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
     Surprise
    -0.11
    plex
    -0.09
    apes
    -0.09
    wer
    -0.09
    Thumb
    -0.09
    782
    -0.09
    raph
    -0.09
     surprise
    -0.09
    aina
    -0.09
     Jacqu
    -0.08
    POSITIVE LOGITS
     Obl
    0.17
     obliged
    0.17
     ob
    0.16
     oblig
    0.14
    obl
    0.14
    incl
    0.12
     opportunity
    0.11
     eager
    0.11
    lbl
    0.10
     Ob
    0.10
    Activations Density 0.011%

    No Known Activations