© 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. 90487
    Prev
    Next
    INDEX
    Explanations

    wealthy families and individuals

    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
    ald
    -0.11
     [#
    -0.10
     consec
    -0.10
    alis
    -0.09
    ajar
    -0.09
    Bookmark
    -0.09
     conjug
    -0.09
    _bm
    -0.09
    lep
    -0.09
    /Form
    -0.09
    POSITIVE LOGITS
     fla
    0.13
     lav
    0.13
    -funded
    0.12
     lifestyle
    0.11
     yacht
    0.11
    ocratic
    0.11
     elit
    0.11
     privileged
    0.10
     afford
    0.10
     privilege
    0.10
    Activations Density 0.095%

    No Known Activations