© 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. 46101
    Prev
    Next
    INDEX
    Explanations

    erection, cancer, loss, enlargement

    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
    ulia
    -0.11
    abbo
    -0.09
     Fres
    -0.09
    itud
    -0.09
     Vaugh
    -0.09
     tir
    -0.09
    akes
    -0.09
     sympt
    -0.08
     showc
    -0.08
    ally
    -0.08
    POSITIVE LOGITS
     enlargement
    0.14
     augmentation
    0.12
     ext
    0.10
     extend
    0.10
     authority
    0.10
     size
    0.09
    olle
    0.09
    818
    0.09
     extending
    0.09
     pumps
    0.09
    Activations Density 0.003%

    No Known Activations