© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by capitalized words

    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
    Quotes
    -0.13
    }\"
    -0.12
    à¹Īา
    -0.11
    .\"
    -0.11
    OutOf
    -0.11
     Sha
    -0.11
    —we
    -0.11
     dat
    -0.11
    <table
    -0.11
    ennen
    -0.11
    POSITIVE LOGITS
    0.14
    ...
    0.09
    ult
    0.09
    0.09
    0.09
    (...)
    0.08
     ...
    0.08
    ide
    0.07
    âĢ¦the
    0.07
     unb
    0.06
    Activations Density 0.156%

    No Known Activations