© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7738
    Prev
    Next
    INDEX
    Explanations

    free downloads

    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
    erp
    -0.12
    antha
    -0.10
     jr
    -0.10
    stadt
    -0.10
    uil
    -0.10
    odia
    -0.10
     conduct
    -0.09
    .extra
    -0.09
    apl
    -0.09
    angen
    -0.09
    POSITIVE LOGITS
     download
    0.17
     downloads
    0.17
    -download
    0.15
    /download
    0.14
     downloadable
    0.14
     online
    0.14
     downloading
    0.12
    downloads
    0.12
    download
    0.12
    _download
    0.12
    Activations Density 0.006%

    No Known Activations