© 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. 113549
    Prev
    Next
    INDEX
    Explanations

    continuous or uninterrupted processes

    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
    erald
    -0.12
    bung
    -0.11
     Hur
    -0.11
    adors
    -0.11
    _until
    -0.11
    squ
    -0.10
     Till
    -0.10
    upert
    -0.10
     Tud
    -0.10
    xr
    -0.10
    POSITIVE LOGITS
     continuity
    0.24
     uninterrupted
    0.23
     pause
    0.22
     seamlessly
    0.22
     seamless
    0.21
     interruption
    0.19
     missed
    0.19
     smoothly
    0.18
     stride
    0.18
     skipping
    0.18
    Activations Density 0.118%

    No Known Activations