© 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. 90207
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ogle
    -0.12
     Bast
    -0.12
     seiz
    -0.12
    oux
    -0.11
     McB
    -0.11
     hol
    -0.10
     severed
    -0.10
     aba
    -0.10
     nag
    -0.10
     encount
    -0.10
    POSITIVE LOGITS
    kok
    0.08
     riv
    0.08
    .astype
    0.08
    iji
    0.08
     irresistible
    0.08
     aan
    0.07
     functionalities
    0.07
     gere
    0.07
     dorm
    0.07
     subscriber
    0.07
    Activations Density 0.000%

    No Known Activations