© 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. 92117
    Prev
    Next
    INDEX
    Explanations

    drag, dragging, dragged

    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
     stamp
    -0.09
    istory
    -0.09
     explic
    -0.08
     Gund
    -0.08
    usto
    -0.08
    cco
    -0.08
     bree
    -0.08
     wandered
    -0.08
     Lamp
    -0.08
     plist
    -0.08
    POSITIVE LOGITS
     across
    0.19
     Across
    0.16
    Across
    0.15
     dragging
    0.13
     drag
    0.13
     dragged
    0.13
     along
    0.12
    along
    0.12
     abrasive
    0.12
     rake
    0.12
    Activations Density 0.021%

    No Known Activations