© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    teaching or instructing

    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
     Stud
    -0.12
     individually
    -0.10
     Polic
    -0.10
     scal
    -0.10
     Pastor
    -0.10
    Sdk
    -0.10
     polic
    -0.10
     Editors
    -0.10
     classmates
    -0.10
     studied
    -0.09
    POSITIVE LOGITS
     teaching
    0.35
     teach
    0.29
     Teaching
    0.26
     teaches
    0.26
     Teach
    0.25
     taught
    0.19
     instruct
    0.19
     classes
    0.19
     lect
    0.19
     teachings
    0.18
    Activations Density 0.495%

    No Known Activations