© 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. 47705
    Prev
    Next
    INDEX
    Explanations

    testing code or asking questions

    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
     Reached
    -0.10
     tast
    -0.08
     hunger
    -0.08
     backward
    -0.08
     cuatro
    -0.08
     Yours
    -0.07
    edo
    -0.07
     lawmaker
    -0.07
     discern
    -0.07
     Cohen
    -0.07
    POSITIVE LOGITS
    -period
    0.10
     Hok
    0.10
     Peng
    0.10
    ocate
    0.09
     uber
    0.09
    athe
    0.09
     Het
    0.09
     Kut
    0.09
    inous
    0.09
     Sys
    0.09
    Activations Density 0.001%

    No Known Activations