© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27231
    Prev
    Next
    INDEX
    Explanations

    illegal activities, violence, harassment

    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
    IRM
    -0.11
     McCabe
    -0.10
     sine
    -0.10
    yla
    -0.10
     reconsider
    -0.10
     Replay
    -0.09
     qualifying
    -0.09
     handwriting
    -0.09
     blush
    -0.09
     mt
    -0.09
    POSITIVE LOGITS
     harass
    0.10
     fet
    0.09
     Anyone
    0.09
     anywhere
    0.09
    iti
    0.09
     kond
    0.09
     inclus
    0.09
     tolerance
    0.09
     cond
    0.09
     anyone
    0.09
    Activations Density 0.013%

    No Known Activations