© 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. 4239
    Prev
    Next
    INDEX
    Explanations

    victims of 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
     stubborn
    -0.12
    æŃ
    -0.10
     disobed
    -0.10
     Death
    -0.10
     obst
    -0.10
    adm
    -0.09
     Jail
    -0.09
    Death
    -0.09
     arrogance
    -0.09
    locs
    -0.09
    POSITIVE LOGITS
     victim
    0.49
     victims
    0.47
     Victims
    0.41
     Victim
    0.38
    victim
    0.37
     harmed
    0.28
     suffering
    0.27
     Vict
    0.27
     affected
    0.27
     suffer
    0.25
    Activations Density 0.623%

    No Known Activations