© 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. 26572
    Prev
    Next
    INDEX
    Explanations

    begin/start actions

    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
     even
    -0.11
    even
    -0.11
     Darling
    -0.11
    avra
    -0.10
    pip
    -0.10
    cea
    -0.10
    	continue
    -0.10
    continue
    -0.10
     throwable
    -0.10
     Continuing
    -0.10
    POSITIVE LOGITS
    å¼Ģå§ĭ
    0.15
     slowly
    0.14
     begin
    0.14
     begins
    0.14
     began
    0.13
     starts
    0.13
     starting
    0.13
     firstly
    0.13
     commenced
    0.13
     start
    0.13
    Activations Density 0.046%

    No Known Activations