© 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. 111718
    Prev
    Next
    INDEX
    Explanations

    that nature

    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
    Not in Any Lists

    No Comments

    Negative Logits
    avy
    -0.09
     litt
    -0.09
    س
    -0.08
     *__
    -0.08
    iddy
    -0.08
    -runner
    -0.08
     sple
    -0.08
    wayne
    -0.07
    empl
    -0.07
     Invest
    -0.07
    POSITIVE LOGITS
     Hansen
    0.10
    ATOM
    0.10
    848
    0.10
     Boot
    0.09
     Sham
    0.09
    ))?
    0.09
     pari
    0.09
     Kö
    0.09
    azzi
    0.09
    eni
    0.09
    Activations Density 0.001%

    No Known Activations