© 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. 51027
    Prev
    Next
    INDEX
    Explanations

    should followed by advice or action

    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
     unknow
    -0.11
     unwilling
    -0.08
     inadvertently
    -0.08
     mistakenly
    -0.08
    ATAL
    -0.07
     produce
    -0.07
     Haven
    -0.07
     spindle
    -0.07
     Peel
    -0.07
     invis
    -0.07
    POSITIVE LOGITS
     beware
    0.31
     consider
    0.20
     remember
    0.19
     Bew
    0.19
    consider
    0.19
     heed
    0.19
     avoid
    0.18
     carefully
    0.17
     consid
    0.17
     careful
    0.17
    Activations Density 0.136%

    No Known Activations