© 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. 33969
    Prev
    Next
    INDEX
    Explanations

    groovy, grover, groves, grozny

    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
     indirect
    -0.09
     Vice
    -0.08
     indirectly
    -0.08
     r
    -0.08
     dense
    -0.08
    aily
    -0.07
    ilen
    -0.07
     indef
    -0.07
     act
    -0.07
     Buck
    -0.07
    POSITIVE LOGITS
    gro
    0.13
    ovy
    0.12
    oving
    0.12
    scopic
    0.12
    isman
    0.12
    slot
    0.12
     Gro
    0.11
    Gro
    0.11
     gro
    0.11
    oves
    0.11
    Activations Density 0.037%

    No Known Activations