© 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. 117578
    Prev
    Next
    INDEX
    Explanations

    within limits or boundaries

    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
    ype
    -0.08
     reck
    -0.08
     retire
    -0.08
     Petit
    -0.08
     discoveries
    -0.08
     lest
    -0.08
     unsur
    -0.08
     Heritage
    -0.08
    icker
    -0.07
     penetrating
    -0.07
    POSITIVE LOGITS
     Kelley
    0.12
    ston
    0.11
     Forget
    0.10
    xes
    0.10
     walls
    0.10
    airs
    0.10
    osto
    0.10
    locker
    0.10
    ZO
    0.10
    itical
    0.10
    Activations Density 0.002%

    No Known Activations