© 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. 26854
    Prev
    Next
    INDEX
    Explanations

    metadata fields

    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
     moderate
    -0.09
     Moderate
    -0.09
     hend
    -0.08
    ","",
    -0.08
    elah
    -0.08
    astle
    -0.08
     Whenever
    -0.08
    Structured
    -0.08
     brass
    -0.08
    uele
    -0.08
    POSITIVE LOGITS
     Date
    0.10
    Keywords
    0.10
     notes
    0.10
     motto
    0.10
     Tess
    0.10
     ballpark
    0.10
    (s
    0.09
     ?:
    0.09
    --------------------------------
    0.09
     timeframe
    0.09
    Activations Density 0.370%

    No Known Activations