© 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. 26508
    Prev
    Next
    INDEX
    Explanations

    lady gaga

    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
     bais
    -0.10
     HUGE
    -0.09
     tranny
    -0.08
    ãĥ¼ãĤ¸
    -0.08
     firstly
    -0.08
     burge
    -0.07
    okino
    -0.07
     Moff
    -0.07
     blat
    -0.07
     basically
    -0.07
    POSITIVE LOGITS
     .↵↵
    0.11
     .↵
    0.11
    —↵↵
    0.10
     Somehow
    0.10
    âĢ¢↵↵
    0.10
     \↵
    0.10
    âĢ¦
    0.10
     cared
    0.10
     couldn
    0.10
    –↵↵
    0.10
    Activations Density 0.001%

    No Known Activations