© 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. 112008
    Prev
    Next
    INDEX
    Explanations

    human temptation and knowledge

    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
     Noah
    -0.11
     ark
    -0.11
     pog
    -0.11
     Ark
    -0.10
     Sanct
    -0.10
     Extras
    -0.10
     Germ
    -0.09
     amo
    -0.09
     germ
    -0.09
     salvage
    -0.09
    POSITIVE LOGITS
     disob
    0.14
     forbidden
    0.14
     tempted
    0.13
     tempting
    0.13
     knowledge
    0.13
     Knowledge
    0.13
     serpent
    0.12
    knowledge
    0.12
     vert
    0.11
    Knowledge
    0.11
    Activations Density 0.031%

    No Known Activations