© 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. 91799
    Prev
    Next
    INDEX
    Explanations

    image and images

    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
     Conversation
    -0.10
     unwrap
    -0.10
     viewpoint
    -0.10
     hinges
    -0.09
     farmhouse
    -0.09
     viewpoints
    -0.09
     hinge
    -0.09
     dryer
    -0.09
     scrut
    -0.09
     bri
    -0.09
    POSITIVE LOGITS
     image
    0.18
     images
    0.17
     Images
    0.17
     Image
    0.16
    Images
    0.15
    image
    0.14
    .Images
    0.13
    .image
    0.13
     IMAGE
    0.13
    images
    0.13
    Activations Density 0.235%

    No Known Activations