© 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. 113256
    Prev
    Next
    INDEX
    Explanations

    course codes and academic terms

    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
     Contributor
    -0.12
    aea
    -0.09
     Frag
    -0.09
     categor
    -0.09
     Committees
    -0.09
     Slate
    -0.09
    agra
    -0.08
     Chase
    -0.08
     kostenlos
    -0.08
    Gratis
    -0.08
    POSITIVE LOGITS
     course
    0.24
     midterm
    0.23
     coursework
    0.22
     semester
    0.21
     Semester
    0.20
    course
    0.20
    _course
    0.20
     Course
    0.19
     courses
    0.19
     assignment
    0.19
    Activations Density 0.563%

    No Known Activations