© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    about this item

    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
     plagiar
    -0.10
     Definition
    -0.10
     prejudice
    -0.09
     humble
    -0.09
     tw
    -0.09
     reverted
    -0.09
    Appear
    -0.09
    nelle
    -0.09
    ãģĿãģĹãģ¦
    -0.09
     Cul
    -0.08
    POSITIVE LOGITS
     product
    0.10
     Describe
    0.09
     ()↵
    0.09
     reviewer
    0.08
    UPI
    0.08
     usage
    0.08
     fred
    0.08
     tear
    0.08
     neh
    0.08
    LBL
    0.08
    Activations Density 0.005%

    No Known Activations