© 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. 50927
    Prev
    Next
    INDEX
    Explanations

    legal/political repercussions

    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
    immel
    -0.10
     urg
    -0.09
    illon
    -0.08
     FAST
    -0.08
     miserable
    -0.08
     fancy
    -0.08
    ihu
    -0.08
     patented
    -0.07
     Cob
    -0.07
     QC
    -0.07
    POSITIVE LOGITS
     repercussions
    0.27
     reperc
    0.24
     judgment
    0.21
     judgement
    0.21
     consequences
    0.20
     ridicule
    0.20
     consequence
    0.19
     backlash
    0.18
     retaliation
    0.18
     embarrassment
    0.18
    Activations Density 0.008%

    No Known Activations