© 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. 34097
    Prev
    Next
    INDEX
    Explanations

    do or accomplish something

    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
    yme
    -0.12
    catid
    -0.11
    eti
    -0.11
     entrega
    -0.11
    Smarty
    -0.11
    nonce
    -0.11
    ãģĿ
    -0.11
    ï¼Ĵï¼IJ
    -0.11
     Ged
    -0.11
    anse
    -0.10
    POSITIVE LOGITS
     something
    0.42
     anything
    0.40
     things
    0.38
     everything
    0.33
    something
    0.31
     stuff
    0.30
     Something
    0.28
    anything
    0.28
     nothing
    0.27
    omething
    0.25
    Activations Density 0.300%

    No Known Activations