© 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. 111592
    Prev
    Next
    INDEX
    Explanations

    her historical novels

    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
     demanding
    -0.09
     ли
    -0.09
    ibi
    -0.08
     diam
    -0.08
     awaiting
    -0.08
    ave
    -0.07
     rape
    -0.07
     bystand
    -0.07
    aben
    -0.07
     Daniels
    -0.07
    POSITIVE LOGITS
     Gardner
    0.11
    ’e
    0.11
    096
    0.11
     doing
    0.10
     handmade
    0.10
     irrespective
    0.10
     bare
    0.10
    doing
    0.10
     *__
    0.10
     Cong
    0.10
    Activations Density 0.026%

    No Known Activations