© 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. 46993
    Prev
    Next
    INDEX
    Explanations

    ways and methods

    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
    way
    -0.12
     ways
    -0.11
     way
    -0.11
    ways
    -0.10
    æĸ¹å¼ı
    -0.08
     Reference
    -0.08
    -way
    -0.08
    .way
    -0.08
     method
    -0.08
     Ways
    -0.08
    POSITIVE LOGITS
     wa
    0.13
    lements
    0.11
    hm
    0.11
     hovering
    0.11
    Jvm
    0.11
     Hew
    0.10
     oy
    0.10
    Rates
    0.10
    iams
    0.10
     Debugger
    0.10
    Activations Density 0.039%

    No Known Activations