© 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. 31269
    Prev
    Next
    INDEX
    Explanations

    people's names and family members

    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
    DAL
    -0.09
     sut
    -0.08
     VOID
    -0.08
    adm
    -0.08
     autos
    -0.08
    /an
    -0.07
    arak
    -0.07
     Staten
    -0.07
     Budd
    -0.07
    DSP
    -0.07
    POSITIVE LOGITS
     loving
    0.14
    /dom
    0.14
     Loving
    0.11
     twee
    0.10
     beloved
    0.10
     domestically
    0.10
     Domestic
    0.10
    pra
    0.10
     domestic
    0.10
     Pride
    0.10
    Activations Density 0.197%

    No Known Activations