© 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. 92054
    Prev
    Next
    INDEX
    Explanations

    daily, dishwasher, serve, solo

    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
     --
    -0.08
     lethal
    -0.08
    DON
    -0.07
     throwable
    -0.07
     stick
    -0.07
     possessed
    -0.07
     gotten
    -0.07
    exception
    -0.07
     potent
    -0.07
    amm
    -0.07
    POSITIVE LOGITS
     Outer
    0.12
     Desired
    0.12
     TBD
    0.12
     Peel
    0.11
     tarn
    0.11
     desired
    0.11
     todd
    0.11
     Inches
    0.11
    Outer
    0.11
     unins
    0.11
    Activations Density 0.028%

    No Known Activations