© 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. 111803
    Prev
    Next
    INDEX
    Explanations

    stream

    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
     Teddy
    -0.09
    inka
    -0.08
     duct
    -0.08
    è²
    -0.07
    ded
    -0.07
    ws
    -0.07
    dbc
    -0.07
     affordability
    -0.07
     dof
    -0.07
     Finch
    -0.07
    POSITIVE LOGITS
     streaming
    0.16
     stream
    0.15
     streams
    0.15
     STREAM
    0.15
     Stream
    0.15
     Streaming
    0.14
    -stream
    0.14
    STREAM
    0.14
     streamed
    0.14
    Streams
    0.13
    Activations Density 0.004%

    No Known Activations