© 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. 117331
    Prev
    Next
    INDEX
    Explanations

    explaining what happened

    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
    ?',
    -0.09
     illeg
    -0.08
     Preston
    -0.08
    æĺ¯åIJ¦
    -0.08
    _fact
    -0.08
     whether
    -0.08
     Mell
    -0.07
     associ
    -0.07
    Toolbar
    -0.07
     WHETHER
    -0.07
    POSITIVE LOGITS
    adin
    0.13
     missing
    0.11
     Sundays
    0.11
     why
    0.11
    Missing
    0.10
    eras
    0.10
    why
    0.10
     TRUE
    0.10
     earlier
    0.10
    uen
    0.10
    Activations Density 0.018%

    No Known Activations