© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    orbital eye implants

    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
     Scalars
    -0.11
     strand
    -0.11
    strand
    -0.09
     Cobb
    -0.09
     seguro
    -0.09
     trot
    -0.09
     hairy
    -0.09
     gig
    -0.09
     Fet
    -0.09
     Bowen
    -0.08
    POSITIVE LOGITS
     bruises
    0.17
     facial
    0.17
     bru
    0.16
     mascara
    0.16
     eye
    0.16
     panda
    0.16
     Makeup
    0.16
     makeup
    0.16
    -eye
    0.15
     wrinkles
    0.15
    Activations Density 0.106%

    No Known Activations