© 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. 113962
    Prev
    Next
    INDEX
    Explanations

    Bastia, bastards, Bastian, Bastille, Bastide

    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
    'h
    -0.10
    lei
    -0.10
     filt
    -0.10
    seo
    -0.10
     |_
    -0.09
     vere
    -0.09
    entar
    -0.09
     financ
    -0.09
    losing
    -0.09
    ushi
    -0.09
    POSITIVE LOGITS
     remorse
    0.09
     universal
    0.08
    ide
    0.08
     promises
    0.08
     conserv
    0.08
     spec
    0.08
    ichen
    0.08
     Nass
    0.08
     Calculates
    0.08
    ocus
    0.08
    Activations Density 0.001%

    No Known Activations