© 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. 114407
    Prev
    Next
    INDEX
    Explanations

    live streaming and broadcast coverage

    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
     hypo
    -0.12
     responsable
    -0.10
     Drag
    -0.10
     onstage
    -0.10
     Simulator
    -0.10
     mentally
    -0.10
     scor
    -0.10
     photographed
    -0.10
    leigh
    -0.10
     trou
    -0.10
    POSITIVE LOGITS
     stream
    0.21
     live
    0.21
     streamed
    0.19
     streams
    0.18
    /stream
    0.17
     LIVE
    0.16
    -stream
    0.16
     Stream
    0.16
     streaming
    0.16
    live
    0.15
    Activations Density 0.153%

    No Known Activations