© 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. 114748
    Prev
    Next
    INDEX
    Explanations

    demonstrating or explaining something

    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
     desirable
    -0.10
     undesirable
    -0.09
    axes
    -0.09
     admittedly
    -0.09
     shorthand
    -0.09
     succes
    -0.09
    Ordered
    -0.09
     functional
    -0.09
    URRE
    -0.09
     unexpectedly
    -0.09
    POSITIVE LOGITS
     bran
    0.13
     ordeal
    0.12
    otto
    0.12
    sted
    0.11
     reasoning
    0.11
     branching
    0.11
     interchangeable
    0.11
     Classification
    0.11
     shed
    0.11
     pertaining
    0.11
    Activations Density 0.316%

    No Known Activations