© 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. 16323
    Prev
    Next
    INDEX
    Explanations

    seeing and perception

    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
    sert
    -0.10
    eco
    -0.09
     Clips
    -0.09
     Garr
    -0.09
    esome
    -0.09
     Moy
    -0.09
    atty
    -0.09
    trad
    -0.08
    azzi
    -0.08
     withheld
    -0.08
    POSITIVE LOGITS
     seeing
    0.39
     sees
    0.38
     Seeing
    0.34
     see
    0.33
    seeing
    0.33
     vision
    0.33
     perceive
    0.31
    Seeing
    0.31
     visible
    0.29
     perception
    0.29
    Activations Density 0.297%

    No Known Activations