© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    URL and code snippets

    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
    ument
    -0.10
    Enlarge
    -0.09
    lev
    -0.08
     ridiculously
    -0.08
    leans
    -0.08
    oret
    -0.08
     impl
    -0.08
    &eacute
    -0.08
    -env
    -0.08
    (deg
    -0.08
    POSITIVE LOGITS
     (@
    0.14
     Instagram
    0.13
     instagram
    0.12
     Tik
    0.11
     alias
    0.11
    (@
    0.11
     herself
    0.11
     daughter
    0.10
    å§
    0.10
     https
    0.10
    Activations Density 0.032%

    No Known Activations