© 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. 30956
    Prev
    Next
    INDEX
    Explanations

    mesh, lattice, cage, basket

    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
     gou
    -0.13
     surfaced
    -0.11
     stub
    -0.11
     seals
    -0.11
     seal
    -0.11
     slab
    -0.11
     slug
    -0.10
    stub
    -0.10
     bunk
    -0.10
    Chunk
    -0.10
    POSITIVE LOGITS
     mesh
    0.31
     cage
    0.31
     cages
    0.27
     Mesh
    0.26
     Cage
    0.26
     meshes
    0.25
    mesh
    0.25
     lattice
    0.23
    Mesh
    0.22
     basket
    0.20
    Activations Density 0.614%

    No Known Activations