© 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. 5137
    Prev
    Next
    INDEX
    Explanations

    pulling and dragging

    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
     sandwich
    -0.12
    icl
    -0.11
     nim
    -0.10
     clap
    -0.10
     Paran
    -0.10
    imar
    -0.10
    itel
    -0.10
    NCY
    -0.10
     Grove
    -0.10
    osta
    -0.10
    POSITIVE LOGITS
     tug
    0.39
     pulling
    0.38
     pull
    0.35
     Pull
    0.34
     pulled
    0.33
    Pull
    0.31
    pull
    0.31
     pulls
    0.31
     dragging
    0.29
     dragged
    0.27
    Activations Density 0.357%

    No Known Activations