© 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. 29959
    Prev
    Next
    INDEX
    Explanations

    visual scenes and images

    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
     attent
    -0.11
     renown
    -0.10
    lays
    -0.10
    plat
    -0.10
    ishlist
    -0.10
    Attention
    -0.09
    861
    -0.09
    webs
    -0.09
    qw
    -0.09
     Bios
    -0.09
    POSITIVE LOGITS
     scene
    0.37
     image
    0.36
     sight
    0.35
     scenes
    0.31
     images
    0.31
     imagery
    0.29
     sights
    0.29
     visuals
    0.28
     Scene
    0.27
     picture
    0.26
    Activations Density 0.136%

    No Known Activations