© 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. 49326
    Prev
    Next
    INDEX
    Explanations

    appearance, walking, visible

    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
     electr
    -0.10
    -anchor
    -0.10
     Chr
    -0.10
    bid
    -0.10
     hed
    -0.09
     Anchor
    -0.09
     Reach
    -0.09
     bid
    -0.09
     pile
    -0.09
    nej
    -0.09
    POSITIVE LOGITS
     appearance
    0.18
     walking
    0.17
     Appearance
    0.16
     public
    0.15
     walk
    0.15
     appearances
    0.15
     visible
    0.14
    appearance
    0.14
     walked
    0.13
     Walk
    0.13
    Activations Density 0.055%

    No Known Activations