© 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. 111589
    Prev
    Next
    INDEX
    Explanations

    completes or finishing

    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
     unint
    -0.09
     Leer
    -0.09
    Blank
    -0.09
    iar
    -0.09
     lo
    -0.09
    sess
    -0.09
     geg
    -0.08
     StringBuffer
    -0.08
     Unt
    -0.08
    loth
    -0.08
    POSITIVE LOGITS
     completes
    0.16
     completing
    0.13
     Comple
    0.12
     completed
    0.12
     rather
    0.11
     Lastly
    0.11
     Completed
    0.11
     Witt
    0.11
     further
    0.10
    Comple
    0.10
    Activations Density 0.032%

    No Known Activations