© 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. 50479
    Prev
    Next
    INDEX
    Explanations

    eyewear or visual aids

    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
     armour
    -0.12
     clothes
    -0.12
     dress
    -0.11
     body
    -0.11
     armor
    -0.11
     coat
    -0.11
     discharge
    -0.10
     Body
    -0.10
     tune
    -0.10
     appropriated
    -0.10
    POSITIVE LOGITS
     laz
    0.12
     tapes
    0.11
     glare
    0.11
     thickness
    0.10
     dio
    0.10
     Glasses
    0.10
     SEAL
    0.10
     folds
    0.10
     Laz
    0.10
     Voices
    0.10
    Activations Density 0.005%

    No Known Activations