© 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. 16508
    Prev
    Next
    INDEX
    Explanations

    consent and continuation

    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
    ella
    -0.09
    734
    -0.09
    lect
    -0.09
    üns
    -0.09
     Belfast
    -0.08
     Castro
    -0.08
    bring
    -0.08
     Cot
    -0.08
    ġ
    -0.08
     quis
    -0.08
    POSITIVE LOGITS
     clicking
    0.13
     submitting
    0.12
     entering
    0.12
     accepting
    0.11
     proceed
    0.11
    apg
    0.11
     proceeding
    0.11
     continue
    0.11
     Swal
    0.11
     acceptance
    0.11
    Activations Density 0.042%

    No Known Activations