© 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. 14115
    Prev
    Next
    INDEX
    Explanations

    mistakes, errors, or glitches

    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
     Garner
    -0.11
     immedi
    -0.11
     Penal
    -0.11
     Salv
    -0.10
     playable
    -0.10
    enha
    -0.10
    byss
    -0.09
     Tent
    -0.09
    /use
    -0.09
     Abr
    -0.09
    POSITIVE LOGITS
     overlooked
    0.23
     oversight
    0.21
     missed
    0.21
     slipped
    0.18
     somehow
    0.18
     slips
    0.17
     mistake
    0.16
     slip
    0.16
     unnoticed
    0.16
     mistakenly
    0.16
    Activations Density 0.569%

    No Known Activations