© 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. 117512
    Prev
    Next
    INDEX
    Explanations

    low or negative states

    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
     Alo
    -0.09
     alo
    -0.08
    affected
    -0.08
     Rash
    -0.08
     ä
    -0.08
    EXT
    -0.08
    Severity
    -0.08
     clumsy
    -0.08
     Fatal
    -0.08
    Heading
    -0.08
    POSITIVE LOGITS
     lows
    0.17
     lowest
    0.17
     bottom
    0.16
     gutter
    0.15
     low
    0.15
    lowest
    0.15
     vile
    0.14
     LOW
    0.14
    -low
    0.14
     depths
    0.14
    Activations Density 0.010%

    No Known Activations