© 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. 88475
    Prev
    Next
    INDEX
    Explanations

    bestselling lists and hits

    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
     procure
    -0.11
    vac
    -0.11
     exchange
    -0.11
    igos
    -0.11
    _exchange
    -0.10
     shortened
    -0.10
     exc
    -0.10
    rips
    -0.10
    gm
    -0.10
     Kush
    -0.10
    POSITIVE LOGITS
     seller
    0.11
    seller
    0.11
    -selling
    0.11
     item
    0.11
     charts
    0.10
     overall
    0.10
     Seller
    0.09
     bestselling
    0.09
     author
    0.09
     category
    0.09
    Activations Density 0.093%

    No Known Activations