© 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. 89221
    Prev
    Next
    INDEX
    Explanations

    pulling or towing

    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
     loosely
    -0.10
     Shaft
    -0.10
     claws
    -0.10
     Rams
    -0.10
     ram
    -0.09
    onto
    -0.09
    akis
    -0.09
    hel
    -0.09
     conserv
    -0.09
     pr
    -0.09
    POSITIVE LOGITS
     hard
    0.13
     upwards
    0.12
     toward
    0.11
     upward
    0.11
     downwards
    0.11
     harder
    0.11
     towards
    0.11
     causing
    0.11
    oward
    0.11
     backward
    0.10
    Activations Density 0.020%

    No Known Activations