© 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. 88399
    Prev
    Next
    INDEX
    Explanations

    incentive and desire for interest

    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
     deserved
    -0.10
     Debate
    -0.10
    typed
    -0.10
     somehow
    -0.10
    647
    -0.10
     vac
    -0.10
     cope
    -0.09
     assumptions
    -0.09
     Humph
    -0.09
     brill
    -0.09
    POSITIVE LOGITS
     incentive
    0.28
     incentiv
    0.25
     incentives
    0.23
     wanting
    0.21
    want
    0.21
     Want
    0.20
     vested
    0.20
     want
    0.20
     incent
    0.19
     desire
    0.19
    Activations Density 0.415%

    No Known Activations