© 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. 116539
    Prev
    Next
    INDEX
    Explanations

    academic years and levels

    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
    vary
    -0.13
     punct
    -0.12
     university
    -0.12
     museums
    -0.11
     toy
    -0.11
     Tib
    -0.11
     sanitized
    -0.11
     encyclopedia
    -0.11
     Asi
    -0.11
     UNIVERSITY
    -0.10
    POSITIVE LOGITS
     seniors
    0.20
     juni
    0.20
     freshmen
    0.18
     junior
    0.18
     senior
    0.17
     sophomore
    0.16
     Senior
    0.16
     soph
    0.16
     freshman
    0.15
     cohort
    0.15
    Activations Density 0.270%

    No Known Activations