© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3682
    Prev
    Next
    INDEX
    Explanations

    supernatural television characters

    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
     Cypress
    -0.10
     Jama
    -0.10
     Khal
    -0.10
     Fairfax
    -0.10
     Cly
    -0.09
    onis
    -0.09
    ŀ
    -0.09
     Andrews
    -0.09
     Sponsor
    -0.09
     Scala
    -0.09
    POSITIVE LOGITS
     Winchester
    0.30
     Dean
    0.29
     Crowley
    0.25
    Dean
    0.25
     Supern
    0.22
     Jensen
    0.21
     dean
    0.21
     Sam
    0.20
     Cast
    0.19
     Lucifer
    0.19
    Activations Density 0.180%

    No Known Activations