© 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. 46810
    Prev
    Next
    INDEX
    Explanations

    a pair of

    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
     pairs
    -0.10
     blanket
    -0.10
    faces
    -0.09
     bitterness
    -0.09
    jak
    -0.08
    acket
    -0.08
    pairs
    -0.08
     Univ
    -0.08
     Mona
    -0.08
     Vad
    -0.08
    POSITIVE LOGITS
     earrings
    0.23
     scissors
    0.23
     goggles
    0.21
     headphones
    0.21
     sunglasses
    0.21
     gloves
    0.20
     shoes
    0.20
     boots
    0.20
     trousers
    0.18
     jeans
    0.18
    Activations Density 0.312%

    No Known Activations