© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49713
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     Aub
    -0.11
    hes
    -0.11
     Cocoa
    -0.10
     Dread
    -0.10
     INST
    -0.10
    zo
    -0.10
     FIL
    -0.09
     åľ
    -0.09
     Dip
    -0.09
     hesitant
    -0.09
    POSITIVE LOGITS
     Sala
    0.08
     Bes
    0.08
     churn
    0.08
    arta
    0.08
     consum
    0.08
    ogne
    0.08
     Atlantis
    0.08
     minib
    0.08
     Thumb
    0.08
     reliably
    0.08
    Activations Density 0.007%

    No Known Activations