© 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. 48101
    Prev
    Next
    INDEX
    Explanations

    slow movement or process

    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
     skipping
    -0.10
    ney
    -0.09
     skips
    -0.09
    aqu
    -0.09
     quer
    -0.09
    ovel
    -0.08
     pilgr
    -0.08
    oved
    -0.08
     dearly
    -0.08
     ingen
    -0.08
    POSITIVE LOGITS
     slowly
    0.14
     inch
    0.14
     asc
    0.12
     pace
    0.12
    -motion
    0.12
     paced
    0.11
     unravel
    0.11
     ascend
    0.11
    .asc
    0.11
     exh
    0.10
    Activations Density 0.018%

    No Known Activations