© 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. 8120
    Prev
    Next
    INDEX
    Explanations

    most common/important/best/advantage

    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
     dere
    -0.10
    047
    -0.10
    iesen
    -0.10
     entra
    -0.10
    ongan
    -0.09
    Crow
    -0.09
     afterward
    -0.09
     Crow
    -0.09
     ditch
    -0.09
     Eisen
    -0.09
    POSITIVE LOGITS
     disadvantage
    0.16
     drawback
    0.15
     difference
    0.15
     downside
    0.15
     advantage
    0.15
     thing
    0.14
     pec
    0.13
     Difference
    0.13
     way
    0.12
     limitation
    0.12
    Activations Density 0.081%

    No Known Activations