© 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. 29428
    Prev
    Next
    INDEX
    Explanations

    he has / had / wins

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Supplementary
    -0.10
     countered
    -0.08
    avity
    -0.08
     unconscious
    -0.08
     instinct
    -0.08
    ansom
    -0.08
     convincing
    -0.08
     then
    -0.08
     Couch
    -0.08
     Andersen
    -0.08
    POSITIVE LOGITS
     hadn
    0.19
     weren
    0.14
     ever
    0.13
     EVER
    0.13
    wer
    0.12
     knew
    0.12
     harm
    0.11
     wer
    0.10
     Wie
    0.10
     harms
    0.10
    Activations Density 0.026%

    No Known Activations