© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    film directed by

    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
     Emmy
    -0.10
     publishing
    -0.10
     Microwave
    -0.09
     Publishing
    -0.09
    æľŁ
    -0.09
    Publish
    -0.09
     retro
    -0.09
     YA
    -0.09
     signature
    -0.08
     paperback
    -0.08
    POSITIVE LOGITS
     Edison
    0.18
     shorts
    0.16
     reels
    0.15
     silent
    0.15
     Lum
    0.14
     screenings
    0.14
     negatives
    0.13
     cellul
    0.13
     Shorts
    0.13
     reel
    0.13
    Activations Density 0.399%

    No Known Activations