© 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. 111795
    Prev
    Next
    INDEX
    Explanations

    social responsibility and duties

    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
    afia
    -0.09
    umin
    -0.09
    quist
    -0.08
     nonetheless
    -0.08
     nevertheless
    -0.08
    466
    -0.08
     Clin
    -0.08
    Prog
    -0.08
    116
    -0.08
     unaffected
    -0.08
    POSITIVE LOGITS
     responsibility
    0.64
     responsibilities
    0.55
     Responsibility
    0.54
     Responsibilities
    0.46
    Respons
    0.46
    respons
    0.45
     respons
    0.44
     RESPONS
    0.41
     responsibly
    0.41
     responsible
    0.36
    Activations Density 0.267%

    No Known Activations