© 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. 89698
    Prev
    Next
    INDEX
    Explanations

    silicone and rubber materials

    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
     Crud
    -0.11
    uti
    -0.09
    lah
    -0.09
     Closet
    -0.09
    uren
    -0.09
     sands
    -0.09
    akt
    -0.09
    abe
    -0.09
    amina
    -0.09
     aft
    -0.09
    POSITIVE LOGITS
    -lined
    0.11
    /pl
    0.11
     Dudley
    0.11
     nicer
    0.10
    -covered
    0.10
     softer
    0.10
    -friendly
    0.10
     friendly
    0.10
     straps
    0.10
     strap
    0.10
    Activations Density 0.010%

    No Known Activations