© 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. 5924
    Prev
    Next
    INDEX
    Explanations

    should shop

    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
    emed
    -0.10
     Pak
    -0.10
    âĶģ
    -0.10
    urb
    -0.10
    urf
    -0.10
    apa
    -0.10
    ISP
    -0.10
    Nam
    -0.09
    SN
    -0.09
    eref
    -0.09
    POSITIVE LOGITS
     watch
    0.27
     seeing
    0.23
     see
    0.23
     saw
    0.23
     hear
    0.23
     watched
    0.22
     watching
    0.22
     witness
    0.22
     sees
    0.21
     hears
    0.21
    Activations Density 0.054%

    No Known Activations