© 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. 112968
    Prev
    Next
    INDEX
    Explanations

    harm or negative consequence appears

    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
     Sov
    -0.09
     Ridley
    -0.08
    HC
    -0.08
     vanity
    -0.08
    avan
    -0.08
    arus
    -0.08
    lsa
    -0.08
    andro
    -0.08
    uger
    -0.08
    /art
    -0.08
    POSITIVE LOGITS
     harm
    0.49
     harmed
    0.38
     harms
    0.37
     harming
    0.36
     Harm
    0.33
     hurt
    0.26
     harmful
    0.24
     hurting
    0.23
     injury
    0.22
     damage
    0.21
    Activations Density 0.140%

    No Known Activations