© 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. 27928
    Prev
    Next
    INDEX
    Explanations

    Sara and Sarah

    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
     Competitive
    -0.13
     competitive
    -0.11
     McCl
    -0.11
     Imperial
    -0.11
     efficiency
    -0.11
    zek
    -0.10
     Foley
    -0.10
     Colon
    -0.10
    etti
    -0.10
     Nimbus
    -0.10
    POSITIVE LOGITS
     Sara
    0.39
     Sarah
    0.29
    Sarah
    0.25
     SAR
    0.23
     sar
    0.21
     Kara
    0.18
    arah
    0.18
    sar
    0.17
    ara
    0.16
     Sar
    0.16
    Activations Density 0.061%

    No Known Activations