© 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. 115895
    Prev
    Next
    INDEX
    Explanations

    academic and professional degrees

    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
    <|fim_middle|>
    -0.09
     Memories
    -0.08
    ieder
    -0.08
     steam
    -0.08
    EK
    -0.07
     inherited
    -0.07
     pi
    -0.07
     indicative
    -0.07
     Skeleton
    -0.07
     gan
    -0.07
    POSITIVE LOGITS
     PhD
    0.30
     Ph
    0.28
     MD
    0.25
    Ph
    0.20
     MBA
    0.19
     Pharm
    0.19
     RN
    0.18
     MPH
    0.18
    MD
    0.17
     MS
    0.16
    Activations Density 0.308%

    No Known Activations