© 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. 49505
    Prev
    Next
    INDEX
    Explanations

    smell the algorithm

    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
     visibility
    -0.10
     visible
    -0.10
     viewing
    -0.10
     Viewing
    -0.09
     viewed
    -0.09
     mirrored
    -0.09
     cleanse
    -0.08
    uell
    -0.08
     look
    -0.08
     observed
    -0.08
    POSITIVE LOGITS
    uda
    0.11
     eman
    0.11
    ativity
    0.11
    RTL
    0.11
     goodness
    0.11
     fabric
    0.11
    INESS
    0.11
     fabrics
    0.11
     firsthand
    0.10
    dera
    0.10
    Activations Density 0.013%

    No Known Activations