© 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. 115208
    Prev
    Next
    INDEX
    Explanations

    strong adj

    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
     Vir
    -0.08
     Zub
    -0.08
    nia
    -0.08
    ajo
    -0.08
     hast
    -0.08
    (deg
    -0.08
    ako
    -0.08
     Hus
    -0.08
     Crawford
    -0.07
     hypers
    -0.07
    POSITIVE LOGITS
    -strong
    0.33
     stronger
    0.32
     weaker
    0.31
     weakest
    0.31
     strongest
    0.31
     Weak
    0.29
    Strong
    0.29
     Strong
    0.29
     strong
    0.28
     weak
    0.28
    Activations Density 0.226%

    No Known Activations