© 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. 29779
    Prev
    Next
    INDEX
    Explanations

    accessories and products

    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
     Moo
    -0.09
     vend
    -0.09
    eded
    -0.09
     strapped
    -0.08
    hots
    -0.08
    otti
    -0.08
    esz
    -0.08
    iss
    -0.08
    ousel
    -0.08
     Recycling
    -0.08
    POSITIVE LOGITS
     kits
    0.23
     accessories
    0.23
     kit
    0.20
     products
    0.19
     Kits
    0.18
     tools
    0.18
     Kit
    0.18
     accessory
    0.18
     enh
    0.16
     Accessories
    0.16
    Activations Density 0.619%

    No Known Activations