© 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. 92431
    Prev
    Next
    INDEX
    Explanations

    ip ranges or codes

    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
     helf
    -0.09
     hei
    -0.09
     stap
    -0.08
    ",-
    -0.08
     Pru
    -0.08
     Female
    -0.08
     Extras
    -0.08
     oblig
    -0.08
     inte
    -0.08
    ::*
    -0.08
    POSITIVE LOGITS
    Await
    0.10
    velle
    0.09
    TRACT
    0.09
    ral
    0.09
    enson
    0.09
     electrom
    0.09
     undergo
    0.08
    ivery
    0.08
    amat
    0.08
    elsen
    0.08
    Activations Density 0.008%

    No Known Activations