© 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. 6235
    Prev
    Next
    INDEX
    Explanations

    evil temptation and entities

    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
     offending
    -0.09
     vulgar
    -0.09
     insults
    -0.09
     humiliating
    -0.08
    clc
    -0.08
     suic
    -0.08
     ign
    -0.08
     Hod
    -0.08
    porn
    -0.08
     objection
    -0.08
    POSITIVE LOGITS
     tempting
    0.12
     EV
    0.11
     wicked
    0.10
    Ev
    0.10
    EV
    0.10
     Vill
    0.09
    ango
    0.09
     temptation
    0.09
     evil
    0.09
     tempt
    0.09
    Activations Density 0.185%

    No Known Activations