© 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. 111575
    Prev
    Next
    INDEX
    Explanations

    if you're deciding

    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
    rek
    -0.10
     unfortunately
    -0.10
     Maher
    -0.10
    apo
    -0.09
     Eg
    -0.09
     strangely
    -0.09
     Hog
    -0.08
    GD
    -0.08
     Cat
    -0.08
    elon
    -0.08
    POSITIVE LOGITS
     supposedly
    0.25
     so
    0.18
     truly
    0.17
     allegedly
    0.16
     purported
    0.14
     presumably
    0.13
     Truly
    0.13
     tão
    0.12
     supposed
    0.12
    _so
    0.11
    Activations Density 0.121%

    No Known Activations