© 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. 51013
    Prev
    Next
    INDEX
    Explanations

    punctuation, article titles, and links

    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
    ija
    -0.13
     Conserv
    -0.12
     Dart
    -0.12
    zoom
    -0.11
    cmb
    -0.11
    Zoom
    -0.11
     Zoom
    -0.11
     $#
    -0.11
     Circus
    -0.11
    hopefully
    -0.11
    POSITIVE LOGITS
     Navigation
    0.11
     navigation
    0.11
    iles
    0.09
     âĢİ
    0.08
    âĢİ
    0.08
    ILES
    0.08
     Miy
    0.07
     permalink
    0.07
    0.07
     hyperlink
    0.06
    Activations Density 0.006%

    No Known Activations