© 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. 16365
    Prev
    Next
    INDEX
    Explanations

    beginning or start

    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
     mop
    -0.10
     Inch
    -0.09
     Walters
    -0.09
    undle
    -0.09
     shaft
    -0.09
    abby
    -0.09
     cheat
    -0.09
    brig
    -0.09
     pe
    -0.09
     Garner
    -0.08
    POSITIVE LOGITS
    Began
    0.14
     inception
    0.14
     commenced
    0.13
     dawn
    0.12
     begun
    0.11
     Started
    0.11
     started
    0.11
    194
    0.11
     began
    0.11
     caus
    0.11
    Activations Density 0.672%

    No Known Activations