© 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. 114466
    Prev
    Next
    INDEX
    Explanations

    medical condition 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
     Crack
    -0.10
     Bog
    -0.10
     crack
    -0.10
     McInt
    -0.09
     Mare
    -0.09
    -generated
    -0.09
    ille
    -0.08
     Inf
    -0.08
    ahn
    -0.08
     Revel
    -0.08
    POSITIVE LOGITS
     unknow
    0.11
     success
    0.10
     squir
    0.10
    (strict
    0.10
     formation
    0.10
    abo
    0.10
     cerv
    0.10
     sou
    0.10
    iad
    0.09
    wiki
    0.09
    Activations Density 0.571%

    No Known Activations