© 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. 47558
    Prev
    Next
    INDEX
    Explanations

    scenes and sequences

    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
     storyt
    -0.10
    ardin
    -0.10
     incur
    -0.09
     stories
    -0.09
    strap
    -0.09
    Stories
    -0.09
     Stories
    -0.09
     PX
    -0.09
     plush
    -0.08
     tales
    -0.08
    POSITIVE LOGITS
     scenes
    0.48
     scene
    0.48
     Scene
    0.38
     Scenes
    0.35
    scene
    0.34
    Scene
    0.33
    scenes
    0.32
     sequences
    0.30
    -scenes
    0.28
     sequence
    0.28
    Activations Density 0.477%

    No Known Activations