© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    spray application

    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
    ipl
    -0.10
    iy
    -0.10
    alf
    -0.10
    iens
    -0.09
    oret
    -0.09
    IPP
    -0.09
     sniff
    -0.09
     bdsm
    -0.09
    ie
    -0.09
    cpy
    -0.09
    POSITIVE LOGITS
    dio
    0.11
     everywhere
    0.10
     directional
    0.10
    ocre
    0.09
     across
    0.09
     loose
    0.09
    landers
    0.09
     visionary
    0.09
     Ank
    0.09
    torch
    0.09
    Activations Density 0.008%

    No Known Activations