© 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. 92611
    Prev
    Next
    INDEX
    Explanations

    advocating or opposing viewpoints

    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
     Hawkins
    -0.10
     Impress
    -0.10
     impressions
    -0.10
     arous
    -0.10
     Cabinet
    -0.10
     Checked
    -0.10
    aina
    -0.09
    ouv
    -0.09
    å¾ħ
    -0.09
     Elections
    -0.09
    POSITIVE LOGITS
     advocating
    0.39
     advocate
    0.39
     advocates
    0.39
     advocacy
    0.31
     proponents
    0.31
     Advoc
    0.30
     advocated
    0.30
     advoc
    0.26
     opposed
    0.25
     Advocate
    0.25
    Activations Density 0.546%

    No Known Activations