© 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. 50988
    Prev
    Next
    INDEX
    Explanations

    perceptions, approval, backlash, reactions

    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
     physically
    -0.10
     laz
    -0.10
     grop
    -0.10
     redund
    -0.10
    -calendar
    -0.09
     mnemonic
    -0.09
     pledge
    -0.09
    urge
    -0.09
     urgent
    -0.09
     Sala
    -0.09
    POSITIVE LOGITS
     backlash
    0.17
     ostr
    0.16
     reactions
    0.16
     popularity
    0.16
     Reaction
    0.14
     persecution
    0.14
     conform
    0.13
     Reputation
    0.13
     publicity
    0.13
     Approval
    0.13
    Activations Density 0.062%

    No Known Activations