© 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. 90156
    Prev
    Next
    INDEX
    Explanations

    one million

    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
    oret
    -0.09
    owing
    -0.09
     fois
    -0.09
    ingly
    -0.08
     despite
    -0.08
    -wise
    -0.08
    -less
    -0.08
    -worthy
    -0.08
    que
    -0.08
    !--
    -0.08
    POSITIVE LOGITS
    >manual
    0.08
    inta
    0.08
    BufferData
    0.08
    ´Ī
    0.08
    .Tag
    0.07
     Married
    0.07
    \data
    0.07
    _fw
    0.07
    transfer
    0.07
    empor
    0.07
    Activations Density 15.551%

    No Known Activations