© 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. 117101
    Prev
    Next
    INDEX
    Explanations

    tempted to

    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
     Liebe
    -0.08
     reson
    -0.08
     turbo
    -0.07
     Champagne
    -0.07
     thankful
    -0.07
     stunned
    -0.07
    Declare
    -0.07
     defensively
    -0.07
     depreci
    -0.07
     concern
    -0.07
    POSITIVE LOGITS
     tempt
    0.21
     tempting
    0.20
     temptation
    0.20
     tempted
    0.18
    tempt
    0.17
     lure
    0.16
     beck
    0.16
     tantal
    0.14
     bri
    0.14
     tease
    0.14
    Activations Density 0.010%

    No Known Activations