© 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. 113837
    Prev
    Next
    INDEX
    Explanations

    Major League, Civil, General, histocompatibility

    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
    wares
    -0.09
    yen
    -0.09
     shy
    -0.09
    iron
    -0.09
     Neb
    -0.09
    yers
    -0.09
     miejs
    -0.08
     Sunderland
    -0.08
    TED
    -0.08
    omat
    -0.08
    POSITIVE LOGITS
    /min
    0.23
    -league
    0.22
    itarian
    0.21
     league
    0.19
    -major
    0.16
    -min
    0.15
    itized
    0.15
    ities
    0.15
     League
    0.14
    itary
    0.14
    Activations Density 0.144%

    No Known Activations