© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5419
    Prev
    Next
    INDEX
    Explanations

    recording, filming, production, shoot

    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
     nightly
    -0.11
     listening
    -0.11
    listening
    -0.10
    Listening
    -0.10
     gallery
    -0.10
     attentive
    -0.10
    adopt
    -0.10
     consumption
    -0.09
    rss
    -0.09
     grilled
    -0.09
    POSITIVE LOGITS
     filming
    0.34
     filmed
    0.31
     recording
    0.30
     recordings
    0.24
     Recording
    0.24
     production
    0.23
     shoot
    0.23
     recorded
    0.23
     shoots
    0.22
     productions
    0.22
    Activations Density 0.215%

    No Known Activations