© 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. 111562
    Prev
    Next
    INDEX
    Explanations

    motors and sensors

    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
    were
    -0.10
    'e
    -0.10
     redhead
    -0.09
    plural
    -0.09
    Rol
    -0.09
     earm
    -0.09
     heroine
    -0.09
    trand
    -0.09
     refunded
    -0.09
     were
    -0.08
    POSITIVE LOGITS
    vo
    0.10
     MMI
    0.10
    chied
    0.09
     Clips
    0.09
    ened
    0.09
     antim
    0.09
     Slider
    0.09
     Piper
    0.09
    vor
    0.09
     rigor
    0.08
    Activations Density 0.099%

    No Known Activations