© 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. 13998
    Prev
    Next
    INDEX
    Explanations

    bringing edges back together

    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
     neck
    -0.09
     torso
    -0.08
     deactivated
    -0.08
     grain
    -0.08
     Poll
    -0.08
     abdom
    -0.08
     deactivate
    -0.07
    berry
    -0.07
     straw
    -0.07
     decoding
    -0.07
    POSITIVE LOGITS
    -opening
    0.17
     folded
    0.16
     parted
    0.16
     accordion
    0.16
     fold
    0.16
     opening
    0.15
     folding
    0.15
     opened
    0.15
     open
    0.14
     Opening
    0.14
    Activations Density 0.014%

    No Known Activations