© 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. 116647
    Prev
    Next
    INDEX
    Explanations

    `net` followed by numbers

    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
    202
    -0.38
     covid
    -0.31
     Covid
    -0.30
     COVID
    -0.30
     Biden
    -0.29
    COVID
    -0.27
     pandemic
    -0.26
     Tik
    -0.23
     androidx
    -0.21
     tik
    -0.20
    POSITIVE LOGITS
    201
    0.25
     Zika
    0.24
     Ebola
    0.23
     ISIL
    0.23
     ISIS
    0.22
     Obamacare
    0.21
     Huffington
    0.21
    goo
    0.19
     selfies
    0.18
     millennials
    0.18
    Activations Density 8.156%

    No Known Activations