© 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. 18711
    Prev
    Next
    INDEX
    Explanations

    items held in containers

    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
     Leh
    -0.09
     Bord
    -0.09
     interv
    -0.09
     Miz
    -0.09
     mobil
    -0.09
     Cly
    -0.09
    mas
    -0.09
    adesh
    -0.09
    edes
    -0.09
    vide
    -0.09
    POSITIVE LOGITS
     containing
    0.33
     filled
    0.20
     contain
    0.20
     contains
    0.20
     contents
    0.19
    Containing
    0.19
     full
    0.18
     Contents
    0.16
    contains
    0.16
    Contents
    0.15
    Activations Density 0.425%

    No Known Activations