© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    If you violate

    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
     Dove
    -0.11
     bert
    -0.11
    idge
    -0.11
     morals
    -0.11
    DY
    -0.11
     cared
    -0.11
    lette
    -0.11
    omap
    -0.10
    aku
    -0.10
    lettes
    -0.10
    POSITIVE LOGITS
     violation
    0.15
     Viol
    0.15
     viol
    0.15
     violations
    0.14
     violated
    0.14
     violate
    0.14
     knowingly
    0.14
     violates
    0.13
     repeatedly
    0.13
     violating
    0.12
    Activations Density 0.118%

    No Known Activations