© 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. 46156
    Prev
    Next
    INDEX
    Explanations

    liver regeneration and transplantation

    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
     ejac
    -0.12
     reopen
    -0.12
     shaving
    -0.11
     ejaculation
    -0.11
     shave
    -0.11
     dermat
    -0.11
     electric
    -0.11
     Derm
    -0.11
     molding
    -0.11
     drilled
    -0.10
    POSITIVE LOGITS
     liver
    0.33
     Liver
    0.33
     kidneys
    0.30
     organ
    0.29
     kidney
    0.29
    Liver
    0.27
     renal
    0.26
     neph
    0.25
     hep
    0.25
     bile
    0.24
    Activations Density 3.439%

    No Known Activations