© 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. 51018
    Prev
    Next
    INDEX
    Explanations

    expert perspective

    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
    pare
    -0.12
    ../
    -0.10
    eras
    -0.10
    atos
    -0.10
    eri
    -0.10
    eres
    -0.10
    âĺħ
    -0.10
    enk
    -0.10
    athed
    -0.10
    lest
    -0.10
    POSITIVE LOGITS
    ise
    0.22
    ly
    0.17
    ISE
    0.14
    ises
    0.13
     witness
    0.12
    icity
    0.11
    -level
    0.10
     Witness
    0.10
    ize
    0.09
     witnesses
    0.09
    Activations Density 0.037%

    No Known Activations