© 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. 116689
    Prev
    Next
    INDEX
    Explanations

    Netflix streaming services

    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
     Coy
    -0.09
     canonical
    -0.08
    Canon
    -0.08
     Saddam
    -0.08
    .sms
    -0.08
     Hin
    -0.08
     Coupons
    -0.08
     Sponsor
    -0.08
     Carroll
    -0.08
     handheld
    -0.08
    POSITIVE LOGITS
     Netflix
    0.50
    Netflix
    0.43
    .netflix
    0.32
     binge
    0.29
     streaming
    0.27
    flix
    0.24
     Hulu
    0.22
     Streaming
    0.21
     streamed
    0.21
    Streaming
    0.19
    Activations Density 0.310%

    No Known Activations