© 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. 13953
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
     zipper
    -0.09
     queues
    -0.09
    åĽ
    -0.08
     queue
    -0.08
    abox
    -0.08
    umba
    -0.08
     tubes
    -0.08
    uir
    -0.08
    Accessibility
    -0.08
    priority
    -0.07
    POSITIVE LOGITS
    iar
    0.12
    Arn
    0.10
    è¨ĺäºĭ
    0.10
    yet
    0.09
     curl
    0.09
    enet
    0.09
    beit
    0.09
     Sergio
    0.09
    adel
    0.09
    uar
    0.09
    Activations Density 0.003%

    No Known Activations