© 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. 18618
    Prev
    Next
    INDEX
    Explanations

    questions or clarifications

    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
     seperate
    -0.22
     seper
    -0.17
     distinctly
    -0.14
     ambos
    -0.13
     ninguna
    -0.12
     partly
    -0.12
     prerequisite
    -0.12
     alot
    -0.12
     utilise
    -0.12
     prerequisites
    -0.12
    POSITIVE LOGITS
    º
    0.23
     protagon
    0.23
    ´s
    0.23
     ¿
    0.22
     difer
    0.21
     frec
    0.20
     itens
    0.20
    ª
    0.19
     objet
    0.19
     confort
    0.19
    Activations Density 4.925%

    No Known Activations