© 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. 116225
    Prev
    Next
    INDEX
    Explanations

    fandom speculation about canon

    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
     Craigslist
    -0.11
     frequ
    -0.10
     razor
    -0.09
     gig
    -0.09
     iPhone
    -0.09
     tester
    -0.09
     brag
    -0.09
     Kraft
    -0.09
     Cic
    -0.09
    ?):
    -0.09
    POSITIVE LOGITS
     canon
    0.22
     fandom
    0.20
     fans
    0.17
     canonical
    0.17
     spoilers
    0.17
     Fans
    0.17
    fans
    0.16
     fan
    0.16
     speculation
    0.16
    Fans
    0.15
    Activations Density 0.369%

    No Known Activations