© 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. 89249
    Prev
    Next
    INDEX
    Explanations

    subject assigns, activists fought, employees are

    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
    ussen
    -0.09
    uby
    -0.09
     sided
    -0.08
    obel
    -0.08
    enha
    -0.08
    uele
    -0.07
     pred
    -0.07
    à¸ĩ
    -0.07
    gest
    -0.07
     bid
    -0.07
    POSITIVE LOGITS
     achieved
    0.18
     incurred
    0.16
     undertaken
    0.16
     attained
    0.16
     achievable
    0.14
     endured
    0.14
     imposed
    0.14
     encountered
    0.13
     accomplished
    0.13
     Achie
    0.13
    Activations Density 0.575%

    No Known Activations