© 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. 117527
    Prev
    Next
    INDEX
    Explanations

    at first

    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
     currently
    -0.16
     ultimately
    -0.16
     presently
    -0.14
     meanwhile
    -0.14
     never
    -0.14
     nonetheless
    -0.14
     yet
    -0.13
     beforehand
    -0.13
     unfortunately
    -0.13
     nowadays
    -0.13
    POSITIVE LOGITS
    .Then
    0.15
    Then
    0.14
     Then
    0.12
     merely
    0.12
     sheer
    0.12
    aira
    0.10
     trickle
    0.09
     Amit
    0.09
    kel
    0.09
     unsure
    0.09
    Activations Density 0.098%

    No Known Activations