© 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. 117564
    Prev
    Next
    INDEX
    Explanations

    incidence, fracture, spontaneously

    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
     prostit
    -0.12
     monstr
    -0.11
    quist
    -0.11
     linkage
    -0.10
     Nass
    -0.10
     amore
    -0.10
    _reordered
    -0.10
     Colonial
    -0.10
     Baghd
    -0.10
    ugu
    -0.10
    POSITIVE LOGITS
     [âĢ¦]↵↵
    0.14
     [...]↵↵
    0.11
    Continue
    0.11
    ...
    0.11
    ...↵↵
    0.10
     [âĢ¦
    0.10
     ther
    0.10
     cock
    0.09
     squ
    0.09
     [...]
    0.09
    Activations Density 0.020%

    No Known Activations