© 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. 16183
    Prev
    Next
    INDEX
    Explanations

    pie

    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
     Superman
    -0.10
     bamb
    -0.09
     UTF
    -0.09
     Moy
    -0.08
     UFC
    -0.08
    _subset
    -0.08
     ATH
    -0.08
     Licht
    -0.08
     Haram
    -0.08
     cortisol
    -0.08
    POSITIVE LOGITS
     pie
    0.34
     Pie
    0.33
    Pie
    0.29
     pies
    0.29
     PIE
    0.26
    pie
    0.25
    /pi
    0.20
     Pi
    0.19
     pi
    0.19
     PI
    0.18
    Activations Density 0.237%

    No Known Activations