© 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. 30626
    Prev
    Next
    INDEX
    Explanations

    starting or beginning

    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
     past
    -0.10
    alis
    -0.10
    gue
    -0.09
     late
    -0.09
    during
    -0.09
     later
    -0.09
    iente
    -0.09
    iner
    -0.08
     during
    -0.08
     physic
    -0.08
    POSITIVE LOGITS
     starting
    0.25
     started
    0.25
     start
    0.25
     ìĭľìŀij
    0.23
     initially
    0.23
     initial
    0.23
     originally
    0.23
    start
    0.22
     beginning
    0.22
    -start
    0.22
    Activations Density 0.601%

    No Known Activations