© 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. 25174
    Prev
    Next
    INDEX
    Explanations

    crotch of pants

    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
     peeled
    -0.10
     Bald
    -0.09
     bald
    -0.09
    ija
    -0.09
     Neck
    -0.09
     peel
    -0.09
     towing
    -0.08
     muscular
    -0.07
    utting
    -0.07
     fid
    -0.07
    POSITIVE LOGITS
     crem
    0.13
     confines
    0.13
    seat
    0.12
     pants
    0.12
     rigid
    0.12
    ulis
    0.12
     jeans
    0.11
     seat
    0.11
    ItemCount
    0.11
    antar
    0.11
    Activations Density 0.004%

    No Known Activations