© 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. 112118
    Prev
    Next
    INDEX
    Explanations

    advanced grade education

    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
     Beaut
    -0.11
     beaut
    -0.11
     Carlo
    -0.10
     pseud
    -0.10
    Fat
    -0.09
     Minute
    -0.09
     Replies
    -0.09
     пÑĢи
    -0.09
     settle
    -0.09
     snapshots
    -0.09
    POSITIVE LOGITS
     advanced
    0.22
     accelerated
    0.18
     Advanced
    0.18
     acceleration
    0.17
    advanced
    0.17
     remed
    0.17
     gifted
    0.16
    Advanced
    0.16
     grade
    0.16
     classes
    0.16
    Activations Density 0.226%

    No Known Activations