© 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. 113494
    Prev
    Next
    INDEX
    Explanations

    eyes and coverings

    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
     Rug
    -0.10
     zs
    -0.08
    iaux
    -0.08
     hug
    -0.08
    Protected
    -0.08
     paved
    -0.08
     Brett
    -0.08
    mirror
    -0.08
     Ug
    -0.07
     rug
    -0.07
    POSITIVE LOGITS
     Sight
    0.15
     blind
    0.15
     Blind
    0.13
     ceremon
    0.13
     Eyes
    0.12
     sight
    0.12
     eyes
    0.12
    blind
    0.11
     blinds
    0.11
    ight
    0.11
    Activations Density 0.004%

    No Known Activations