© 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. 48667
    Prev
    Next
    INDEX
    Explanations

    social media and websites

    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
     Ler
    -0.08
    <|fim_middle|>
    -0.08
     generalized
    -0.07
     background
    -0.07
     cur
    -0.07
     soci
    -0.07
    plusplus
    -0.06
     intermediate
    -0.06
     Cary
    -0.06
     Oz
    -0.06
    POSITIVE LOGITS
     Voll
    0.13
     awaiting
    0.13
    bett
    0.12
     Welcome
    0.12
    hus
    0.11
    unic
    0.11
    Loads
    0.11
    welcome
    0.11
    dana
    0.11
    spa
    0.11
    Activations Density 0.002%

    No Known Activations