© 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. 116211
    Prev
    Next
    INDEX
    Explanations

    biography and celebrity information

    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
    axis
    -0.10
    bles
    -0.10
     bleed
    -0.09
     lur
    -0.09
    membership
    -0.08
    registration
    -0.08
     thematic
    -0.08
     vign
    -0.08
     cre
    -0.08
     Seed
    -0.08
    POSITIVE LOGITS
     Biography
    0.25
     biography
    0.22
     Celebrity
    0.19
     celebrity
    0.18
     BIO
    0.17
     celebrities
    0.15
     bi
    0.15
     Wiki
    0.15
    Bi
    0.15
     IMDb
    0.14
    Activations Density 0.151%

    No Known Activations