© 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. 8016
    Prev
    Next
    INDEX
    Explanations

    because, since, thanks

    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
    ships
    -0.10
    ings
    -0.10
    mates
    -0.10
    anges
    -0.10
    (es
    -0.10
    elin
    -0.09
    äºİ
    -0.09
    als
    -0.09
     there
    -0.08
    lining
    -0.08
    POSITIVE LOGITS
    enso
    0.11
     cél
    0.10
    him
    0.09
    же
    0.09
    ffer
    0.09
    Cases
    0.09
     Rosenstein
    0.09
    ira
    0.09
    frei
    0.09
    <<<<
    0.08
    Activations Density 0.011%

    No Known Activations