© 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. 87851
    Prev
    Next
    INDEX
    Explanations

    husted

    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
    uD
    -0.09
     Emanuel
    -0.09
     Jeb
    -0.09
    foon
    -0.09
    adoo
    -0.09
     ine
    -0.09
     Olsen
    -0.09
     Box
    -0.09
     dept
    -0.08
     Pemb
    -0.08
    POSITIVE LOGITS
    _marshall
    0.15
    chandle
    0.13
    js
    0.13
    porter
    0.12
    pdev
    0.12
    marshall
    0.12
    acyj
    0.11
    maries
    0.11
    smith
    0.10
    pmat
    0.10
    Activations Density 0.175%

    No Known Activations