© 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. 48332
    Prev
    Next
    INDEX
    Explanations

    afterwards or nearby

    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
     carn
    -0.11
    OTT
    -0.10
     lul
    -0.10
    rax
    -0.10
     Agility
    -0.10
    SKIP
    -0.10
     när
    -0.10
    463
    -0.10
    instrument
    -0.10
    FAILED
    -0.10
    POSITIVE LOGITS
     afterwards
    0.34
     afterward
    0.33
     thereafter
    0.30
     accompanying
    0.24
     nearby
    0.23
     underneath
    0.21
     Afterwards
    0.21
     simultaneously
    0.20
     subsequently
    0.19
     accompany
    0.18
    Activations Density 0.437%

    No Known Activations