© 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. 91826
    Prev
    Next
    INDEX
    Explanations

    best potential

    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
     invers
    -0.10
    UV
    -0.10
     alg
    -0.09
    inea
    -0.09
     trail
    -0.08
    amer
    -0.08
    orsch
    -0.08
    ector
    -0.08
     sane
    -0.08
     Alg
    -0.08
    POSITIVE LOGITS
     potential
    0.29
     fullest
    0.27
     maxim
    0.26
     maximum
    0.26
     potentials
    0.26
     Potential
    0.25
     maximal
    0.25
    potential
    0.25
     maximize
    0.25
     maximizing
    0.24
    Activations Density 0.216%

    No Known Activations