© 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. 18531
    Prev
    Next
    INDEX
    Explanations

    negative events and actions

    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
    éĩį
    -0.09
     Nice
    -0.09
     transl
    -0.08
     CRS
    -0.08
     gre
    -0.08
     belly
    -0.08
     precinct
    -0.08
    ko
    -0.08
     modal
    -0.08
    iva
    -0.08
    POSITIVE LOGITS
    cio
    0.12
     pulses
    0.10
     irreversible
    0.10
    opus
    0.09
     Nov
    0.09
     plagued
    0.09
    POOL
    0.09
     Fir
    0.09
    -su
    0.09
    fir
    0.09
    Activations Density 0.002%

    No Known Activations