© 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. 46093
    Prev
    Next
    INDEX
    Explanations

    a palindromic phrase prints

    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
     goodies
    -0.11
     dope
    -0.11
     chops
    -0.10
     crossword
    -0.10
     Huck
    -0.10
     vocab
    -0.10
     boo
    -0.09
     grades
    -0.09
    Grade
    -0.09
    clair
    -0.09
    POSITIVE LOGITS
     XK
    0.18
     recursive
    0.16
     recursively
    0.15
    recursive
    0.14
     Meta
    0.13
     posting
    0.13
    meta
    0.13
     meta
    0.13
     Colbert
    0.13
     zal
    0.12
    Activations Density 0.089%

    No Known Activations