© 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. 16879
    Prev
    Next
    INDEX
    Explanations

    initiate

    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
     toggle
    -0.10
     thumb
    -0.09
     twilight
    -0.09
     togg
    -0.08
     Mic
    -0.08
    auen
    -0.08
     Toggle
    -0.08
    /debug
    -0.08
    thumb
    -0.08
    /thumb
    -0.08
    POSITIVE LOGITS
     initiated
    0.62
     initiate
    0.62
     initi
    0.60
     initiating
    0.58
     initiative
    0.57
     initiation
    0.56
    -init
    0.56
     Init
    0.54
     Initi
    0.52
     initiator
    0.51
    Activations Density 0.271%

    No Known Activations