© 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. 114793
    Prev
    Next
    INDEX
    Explanations

    cause harm or damage

    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
    aban
    -0.10
    gger
    -0.10
    anian
    -0.09
    azzi
    -0.09
    anzi
    -0.09
     ked
    -0.09
     unfavor
    -0.09
     Fors
    -0.09
     affinity
    -0.09
     propositions
    -0.09
    POSITIVE LOGITS
     upon
    0.18
     harm
    0.18
     damage
    0.17
    upon
    0.15
     Upon
    0.15
     pain
    0.14
     Damage
    0.14
    Upon
    0.13
     wounds
    0.13
     casualties
    0.12
    Activations Density 0.011%

    No Known Activations