© 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. 26847
    Prev
    Next
    INDEX
    Explanations

    broadcasting, power, pairing, PM, your, MIT, days, :

    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
    pras
    -0.09
    imers
    -0.09
     Carter
    -0.08
    uci
    -0.08
    IFF
    -0.08
    ovich
    -0.08
    stick
    -0.08
    essen
    -0.08
    ritz
    -0.08
    Ops
    -0.08
    POSITIVE LOGITS
     prostitu
    0.10
     oneself
    0.10
    ëı
    0.10
    /Dk
    0.10
     troub
    0.09
     unlaw
    0.09
    Unchecked
    0.09
    emit
    0.09
     pang
    0.09
     unlawful
    0.09
    Activations Density 0.002%

    No Known Activations