© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15848
    Prev
    Next
    INDEX
    Explanations

    embedded structures

    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
    ackers
    -0.10
    stab
    -0.09
    uru
    -0.09
     ultr
    -0.09
     Vu
    -0.09
     Madd
    -0.09
    adia
    -0.09
     Quad
    -0.09
     basket
    -0.08
    inas
    -0.08
    POSITIVE LOGITS
     wall
    0.19
     embedded
    0.18
     floor
    0.17
     walls
    0.15
     Embedded
    0.15
    embedded
    0.14
     embed
    0.14
     underground
    0.14
    -wall
    0.14
    Embedded
    0.13
    Activations Density 0.277%

    No Known Activations