© 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. 30096
    Prev
    Next
    INDEX
    Explanations

    ego, vanity, greed

    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
    inha
    -0.12
    enu
    -0.11
     blessings
    -0.10
     digest
    -0.10
     Campos
    -0.09
    shal
    -0.09
     lique
    -0.09
     affairs
    -0.09
    HashCode
    -0.09
     deserving
    -0.09
    POSITIVE LOGITS
     vanity
    0.30
     ego
    0.26
     curiosity
    0.24
     greed
    0.22
     pride
    0.22
     Vanity
    0.19
     eg
    0.17
     narciss
    0.16
     patriotism
    0.15
     imagination
    0.15
    Activations Density 0.079%

    No Known Activations