© 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. 17254
    Prev
    Next
    INDEX
    Explanations

    diagnosis, treatment, management

    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
     diagnosis
    -0.11
     diagnosed
    -0.10
     diagnose
    -0.10
    nde
    -0.10
     greetings
    -0.10
    ÃŃas
    -0.09
    åĭ
    -0.09
     bacon
    -0.09
    loy
    -0.09
     diagnoses
    -0.09
    POSITIVE LOGITS
    plist
    0.09
     prognosis
    0.09
     Alg
    0.08
     progn
    0.08
     Goldman
    0.08
     Alger
    0.08
    ugu
    0.08
     Warwick
    0.07
     Crescent
    0.07
     Jam
    0.07
    Activations Density 0.085%

    No Known Activations