© 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. 115016
    Prev
    Next
    INDEX
    Explanations

    versions of words or concepts

    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
    624
    -0.08
    immel
    -0.08
    sst
    -0.08
    356
    -0.08
    	namespace
    -0.08
    exus
    -0.08
     unin
    -0.08
     retired
    -0.07
    etas
    -0.07
    764
    -0.07
    POSITIVE LOGITS
    ized
    0.15
     version
    0.14
     versions
    0.14
     counterparts
    0.13
    ified
    0.12
    ised
    0.12
    -version
    0.12
    -enabled
    0.11
    -generated
    0.11
    -encoded
    0.11
    Activations Density 0.600%

    No Known Activations