© 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. 111587
    Prev
    Next
    INDEX
    Explanations

    perinatal, per, cord

    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
    Parm
    -0.09
     Murder
    -0.08
    poke
    -0.08
     disrupted
    -0.08
    ilia
    -0.08
    sty
    -0.08
     wash
    -0.08
     adel
    -0.08
    borg
    -0.08
     starter
    -0.08
    POSITIVE LOGITS
    /per
    0.18
    .Per
    0.11
    (per
    0.10
    .per
    0.10
    -per
    0.09
    ylim
    0.09
    лÑĮ
    0.09
    abeth
    0.09
    SCO
    0.09
     unc
    0.09
    Activations Density 0.138%

    No Known Activations