© 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. 26672
    Prev
    Next
    INDEX
    Explanations

    early and rapid

    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
     instantly
    -0.18
     instant
    -0.14
     immediately
    -0.13
     quickly
    -0.13
     easily
    -0.13
     instantaneous
    -0.12
     fast
    -0.12
     effortlessly
    -0.12
     immediate
    -0.12
     suddenly
    -0.11
    POSITIVE LOGITS
     commencement
    0.12
     thereafter
    0.11
    ehler
    0.11
     grat
    0.10
     (<
    0.10
     commenced
    0.10
     commence
    0.10
     started
    0.09
     Getting
    0.09
     afterward
    0.09
    Activations Density 0.074%

    No Known Activations