© 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. 117598
    Prev
    Next
    INDEX
    Explanations

    finger actions and parts

    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
    ogo
    -0.10
    ashes
    -0.09
     #####
    -0.09
     simul
    -0.09
     spit
    -0.09
     crank
    -0.09
    ulin
    -0.09
    akh
    -0.09
    izio
    -0.09
    anh
    -0.09
    POSITIVE LOGITS
     probing
    0.11
     Lac
    0.10
     digging
    0.10
     tracing
    0.10
     intertwined
    0.10
     nerv
    0.09
     lace
    0.09
    lac
    0.09
     rif
    0.09
     excuses
    0.09
    Activations Density 0.011%

    No Known Activations