© 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. 45965
    Prev
    Next
    INDEX
    Explanations

    insurance quotes

    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
    Negative Logits
     ðĿ
    -0.12
     âĢ¦.
    -0.12
     meanwhile
    -0.11
     âĢ¦
    -0.11
     “âĢ¦
    -0.11
     ward
    -0.10
     _______,
    -0.10
     Tradable
    -0.10
     upstairs
    -0.10
    Ìģ
    -0.10
    POSITIVE LOGITS
     penis
    0.09
     cruising
    0.09
    jaw
    0.08
     testimonials
    0.08
     affiliate
    0.07
     acheter
    0.07
     discounts
    0.07
     loads
    0.07
     visite
    0.07
     PSA
    0.07
    Activations Density 0.014%

    No Known Activations