© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    not actually understanding or capable

    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
     artificial
    -0.10
     leisure
    -0.10
     selfish
    -0.09
     rigid
    -0.08
     indul
    -0.08
     lax
    -0.08
     Arbitrary
    -0.08
     Artificial
    -0.08
     Leisure
    -0.08
     artificially
    -0.08
    POSITIVE LOGITS
     genuine
    0.18
     genuinely
    0.18
     decency
    0.17
     sincerity
    0.16
     sincere
    0.16
     Respect
    0.16
     respect
    0.16
     accountability
    0.15
     legitimately
    0.15
     sincerely
    0.15
    Activations Density 0.159%

    No Known Activations