© 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. 113932
    Prev
    Next
    INDEX
    Explanations

    eyelid and eye conditions

    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
    iente
    -0.10
     Fence
    -0.09
    plug
    -0.09
     elbow
    -0.09
     plug
    -0.09
    ril
    -0.09
     kir
    -0.09
    OTA
    -0.08
    berger
    -0.08
     fenced
    -0.08
    POSITIVE LOGITS
     flutter
    0.17
     blink
    0.16
     blinked
    0.15
     blinking
    0.13
     dro
    0.13
     weighted
    0.13
     heavy
    0.12
     Blink
    0.12
     pup
    0.12
     rested
    0.11
    Activations Density 0.024%

    No Known Activations