© 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. 32553
    Prev
    Next
    INDEX
    Explanations

    consulting doctor or physician

    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
     compartment
    -0.09
     stem
    -0.08
     hap
    -0.08
    ikt
    -0.08
    UMMY
    -0.08
     Blues
    -0.08
     Kn
    -0.07
     Hoy
    -0.07
     Melee
    -0.07
    ael
    -0.07
    POSITIVE LOGITS
     consult
    0.29
     doctor
    0.29
     consultation
    0.28
     Consult
    0.28
     consulting
    0.25
     consulted
    0.25
    consult
    0.24
     physician
    0.24
     doctors
    0.24
     medical
    0.23
    Activations Density 0.328%

    No Known Activations