© 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. 117429
    Prev
    Next
    INDEX
    Explanations

    dynamic

    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
     undone
    -0.10
     mn
    -0.10
    BOT
    -0.09
    byn
    -0.08
     Registration
    -0.08
    mov
    -0.08
    atron
    -0.08
     AUTHORS
    -0.08
     Dennis
    -0.08
    aign
    -0.08
    POSITIVE LOGITS
     outr
    0.09
    unsch
    0.09
     barr
    0.09
    anel
    0.08
    sg
    0.08
    idious
    0.08
    -heart
    0.08
    sam
    0.08
     Amar
    0.08
    elon
    0.08
    Activations Density 0.004%

    No Known Activations