© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31933
    Prev
    Next
    INDEX
    Explanations

    medical conditions and complaints

    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
     gle
    -0.10
     purposely
    -0.10
     wil
    -0.10
     Gle
    -0.10
    ulu
    -0.10
    okit
    -0.10
    ause
    -0.09
    oor
    -0.09
    riot
    -0.09
    ucz
    -0.09
    POSITIVE LOGITS
     inexp
    0.19
     intermitt
    0.17
     attributed
    0.16
     myster
    0.16
     attributable
    0.14
     persist
    0.14
     unrelated
    0.14
    attrib
    0.14
     spor
    0.13
     mysterious
    0.12
    Activations Density 1.003%

    No Known Activations