© 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. 32269
    Prev
    Next
    INDEX
    Explanations

    borderlands, indigenous, adjacent

    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
     Hudson
    -0.09
     Naruto
    -0.09
     '''
    -0.08
    æ´
    -0.08
     Ultimate
    -0.08
     Shark
    -0.08
     rant
    -0.08
    Ult
    -0.08
     Spike
    -0.08
     ras
    -0.07
    POSITIVE LOGITS
     cassette
    0.13
     queer
    0.13
     Netflix
    0.12
    Netflix
    0.11
     psyched
    0.11
     adjacent
    0.11
     adjacency
    0.11
     Gors
    0.11
     Indigenous
    0.11
    gif
    0.10
    Activations Density 0.482%

    No Known Activations