© 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. 50910
    Prev
    Next
    INDEX
    Explanations

    “

    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
     encount
    -0.09
    zimmer
    -0.08
    bung
    -0.07
    [of
    -0.07
    FG
    -0.07
    [
    -0.07
     Kel
    -0.07
     nack
    -0.07
    bel
    -0.07
     sak
    -0.07
    POSITIVE LOGITS
     hinted
    0.11
    []"
    0.11
    Indexed
    0.11
     domingo
    0.10
     pró
    0.10
     multim
    0.10
    __;
    0.10
    998
    0.10
     abril
    0.10
    scanf
    0.09
    Activations Density 0.017%

    No Known Activations