© 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. 30589
    Prev
    Next
    INDEX
    Explanations

    medical and biological suffixes

    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
    ager
    -0.09
    Pres
    -0.08
    iated
    -0.08
     Prescott
    -0.08
     uni
    -0.08
     rendez
    -0.07
    acad
    -0.07
     Mighty
    -0.07
     detriment
    -0.07
     blessings
    -0.07
    POSITIVE LOGITS
    ism
    0.18
    obia
    0.13
    emia
    0.13
    ISM
    0.12
    bia
    0.12
    isis
    0.12
     tendencies
    0.11
    uria
    0.11
    ophilia
    0.11
    idity
    0.11
    Activations Density 0.841%

    No Known Activations