© 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. 29032
    Prev
    Next
    INDEX
    Explanations

    celebrities and famous people

    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
     handmade
    -0.11
     buyer
    -0.11
     Grandma
    -0.11
    CHANT
    -0.10
    ottom
    -0.10
    werp
    -0.10
    Reviewer
    -0.10
     poems
    -0.09
     classrooms
    -0.09
    quil
    -0.09
    POSITIVE LOGITS
     celebrities
    0.56
     celebrity
    0.54
     Celebrity
    0.43
     cele
    0.42
     Cele
    0.34
     famous
    0.29
     stars
    0.29
    cele
    0.28
     superstar
    0.27
     Hollywood
    0.26
    Activations Density 0.320%

    No Known Activations