© 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. 33955
    Prev
    Next
    INDEX
    Explanations

    optics and physics

    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
    /sl
    -0.12
    -sl
    -0.11
     disarm
    -0.11
    Hands
    -0.11
    ume
    -0.11
     fing
    -0.11
     NRA
    -0.11
     cruise
    -0.11
     curl
    -0.11
     sliding
    -0.11
    POSITIVE LOGITS
     bounce
    0.53
     bouncing
    0.50
     jumping
    0.49
     jump
    0.47
     Jump
    0.46
     jumps
    0.44
     bounced
    0.43
    jump
    0.40
    Jump
    0.40
    bounce
    0.40
    Activations Density 0.190%

    No Known Activations