© 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. 113471
    Prev
    Next
    INDEX
    Explanations

    filtering and selecting options

    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
    ihar
    -0.11
     Forbidden
    -0.11
    vae
    -0.11
     prohibited
    -0.11
     Feng
    -0.10
    thy
    -0.10
    æĢģ
    -0.10
     woll
    -0.10
    neutral
    -0.10
     Forums
    -0.10
    POSITIVE LOGITS
     narrow
    0.11
     narrowing
    0.11
     helps
    0.10
     help
    0.10
     helping
    0.10
     based
    0.10
     allowing
    0.10
     narrowed
    0.10
     Narrow
    0.09
     gal
    0.09
    Activations Density 0.084%

    No Known Activations