© 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. 115392
    Prev
    Next
    INDEX
    Explanations

    when it

    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
     rap
    -0.08
     punct
    -0.07
     gram
    -0.07
    inem
    -0.07
    gram
    -0.07
    Gram
    -0.07
     ath
    -0.07
     aerial
    -0.07
     commas
    -0.07
     Rap
    -0.07
    POSITIVE LOGITS
    ocy
    0.12
    /world
    0.11
    оз
    0.11
    irim
    0.11
     lag
    0.11
     poz
    0.11
     Neon
    0.10
    /dd
    0.10
    /help
    0.10
    ahl
    0.10
    Activations Density 0.001%

    No Known Activations