© 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. 29297
    Prev
    Next
    INDEX
    Explanations

    questions or examples

    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
    enos
    -0.09
    PrimaryKey
    -0.09
    )\↵
    -0.09
    chet
    -0.09
    CreateTime
    -0.09
    aux
    -0.09
    WORD
    -0.09
    .kode
    -0.09
     Shade
    -0.09
    áb
    -0.08
    POSITIVE LOGITS
    “I
    0.15
     “
    0.14
    "I
    0.14
     “[
    0.13
    “You
    0.12
     "
    0.12
    .“
    0.12
    “We
    0.11
    “My
    0.11
    :"
    0.11
    Activations Density 0.371%

    No Known Activations