© 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. 89119
    Prev
    Next
    INDEX
    Explanations

    medical and technical 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
    __,__
    -0.09
     fuck
    -0.09
    umba
    -0.09
     vulner
    -0.08
     Lagos
    -0.08
     Cairo
    -0.08
    ,st
    -0.08
    adal
    -0.08
    ...,
    -0.08
    cies
    -0.08
    POSITIVE LOGITS
    away
    0.10
    legs
    0.09
    )!
    0.09
    fox
    0.09
    ange
    0.09
    Listener
    0.09
     oneself
    0.09
    {text
    0.08
    	of
    0.08
    ledo
    0.08
    Activations Density 0.002%

    No Known Activations