© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    hand gripping actions

    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
    Negative Logits
     credited
    -0.13
    uru
    -0.11
     Ups
    -0.10
    .ant
    -0.09
     Monaco
    -0.09
    atel
    -0.09
     Urb
    -0.09
    fel
    -0.09
     stacking
    -0.09
     scram
    -0.09
    POSITIVE LOGITS
     gently
    0.12
    hold
    0.12
     hold
    0.12
     firmly
    0.11
     knobs
    0.11
     Shaft
    0.10
     molding
    0.10
     Hold
    0.10
    tit
    0.10
     tightly
    0.10
    Activations Density 0.102%

    No Known Activations