© 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. 7988
    Prev
    Next
    INDEX
    Explanations

    that followed by consequence or explanation

    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
    asaki
    -0.09
    agli
    -0.09
     amb
    -0.09
     commend
    -0.09
    agu
    -0.09
    ?!
    -0.09
     Conditioning
    -0.09
    oby
    -0.08
    hard
    -0.08
    irm
    -0.08
    POSITIVE LOGITS
     way
    0.25
     Way
    0.15
     lest
    0.13
     WAY
    0.13
     ensures
    0.13
    -way
    0.12
    way
    0.12
    _way
    0.12
    .way
    0.11
     ways
    0.10
    Activations Density 0.049%

    No Known Activations