© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    giving approval or consent

    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
    .false
    -0.10
     Ow
    -0.10
     Tire
    -0.10
    illi
    -0.10
     rever
    -0.09
    565
    -0.09
    onus
    -0.09
    ainer
    -0.09
     Persistence
    -0.09
     usur
    -0.09
    POSITIVE LOGITS
     approve
    0.39
     consent
    0.38
     permission
    0.38
     approval
    0.37
     approves
    0.35
     approving
    0.31
     Approval
    0.31
     approved
    0.31
     approvals
    0.30
     permitting
    0.30
    Activations Density 0.252%

    No Known Activations