© 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. 25376
    Prev
    Next
    INDEX
    Explanations

    examinations and college admissions

    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
     lobbyist
    -0.10
    ucci
    -0.09
    pack
    -0.09
     grad
    -0.08
     Ital
    -0.08
     Calvin
    -0.08
     Germ
    -0.08
    asl
    -0.08
     Pack
    -0.08
     Sequ
    -0.08
    POSITIVE LOGITS
     Examination
    0.19
     exam
    0.19
     examination
    0.19
     exams
    0.18
     examinations
    0.18
     hostel
    0.17
     admission
    0.16
     Entrance
    0.16
     syll
    0.15
     Exam
    0.15
    Activations Density 0.498%

    No Known Activations