© 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. 50826
    Prev
    Next
    INDEX
    Explanations

    writing notes

    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
    _imag
    -0.10
     aire
    -0.10
     bild
    -0.10
     Invocation
    -0.09
     enam
    -0.09
     itk
    -0.09
    imagin
    -0.09
     Imaging
    -0.09
    edImage
    -0.09
     bou
    -0.09
    POSITIVE LOGITS
     notes
    0.62
     Notes
    0.50
    notes
    0.48
    -notes
    0.45
     note
    0.45
    Notes
    0.45
     jot
    0.39
    _notes
    0.38
     NOTES
    0.38
     notebook
    0.36
    Activations Density 0.194%

    No Known Activations