© 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. 111479
    Prev
    Next
    INDEX
    Explanations

    access or permissions

    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
    cba
    -0.11
    uste
    -0.10
    ums
    -0.10
     heavily
    -0.09
     Lance
    -0.09
     unus
    -0.09
    ads
    -0.09
    /System
    -0.09
    incorrect
    -0.09
     incorrect
    -0.09
    POSITIVE LOGITS
     legally
    0.13
     Restricted
    0.09
     according
    0.09
     publicly
    0.09
    lla
    0.08
     Priv
    0.08
     restricted
    0.08
    shal
    0.08
     Tower
    0.08
     boss
    0.08
    Activations Density 0.074%

    No Known Activations