© 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. 26779
    Prev
    Next
    INDEX
    Explanations

    participate in or enjoy something

    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
     lure
    -0.11
     refr
    -0.11
     tempting
    -0.10
     tempted
    -0.10
    reds
    -0.10
     triumph
    -0.09
    loo
    -0.09
     lust
    -0.09
     wreak
    -0.09
     alcoholic
    -0.09
    POSITIVE LOGITS
     being
    0.24
     receiving
    0.23
    è¢
    0.23
    being
    0.21
     Being
    0.20
    Being
    0.20
     receive
    0.17
     attention
    0.16
     receives
    0.15
     losing
    0.15
    Activations Density 0.097%

    No Known Activations