© 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. 32248
    Prev
    Next
    INDEX
    Explanations

    prioritizing self or others

    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
     credibility
    -0.11
     familiarity
    -0.10
     banc
    -0.10
    cleanup
    -0.10
    tam
    -0.10
     cach
    -0.10
    quat
    -0.10
    stadt
    -0.09
    PACE
    -0.09
    zar
    -0.09
    POSITIVE LOGITS
     selfish
    0.66
     priorit
    0.30
     altru
    0.28
     narciss
    0.27
     Self
    0.27
     self
    0.26
     SELF
    0.26
     caring
    0.26
     prioritize
    0.26
     ego
    0.25
    Activations Density 0.238%

    No Known Activations