© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4292
    Prev
    Next
    INDEX
    Explanations

    prohibiting or banning specific things

    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
     virtue
    -0.12
     virt
    -0.12
     complying
    -0.11
     policym
    -0.11
     obe
    -0.11
     Sacred
    -0.10
     Mounted
    -0.10
    vim
    -0.10
    Mounted
    -0.10
     Rae
    -0.10
    POSITIVE LOGITS
     knowingly
    0.13
     selling
    0.12
     sale
    0.12
     interstate
    0.12
     possession
    0.12
     possessing
    0.12
     discrimination
    0.11
     pyramid
    0.11
     minors
    0.10
     solic
    0.10
    Activations Density 0.282%

    No Known Activations